demo: love-humanity knob (funny alignment demo)

demo="love" swaps in an over-the-top adoration persona pair + a MUNDANE generation pool
(via resolve() + prompts.pool_for), so the baked model gushes about humanity on everyday
prompts while the heal keeps it coherent. demo="authority" (default) is unchanged.

- config: demo knob + LOVE_POS/LOVE_NEG preset.
- prompts: MUNDANE pool (mix of people-openings for reliable signal + pure-mundane for the
  comedy gap) + pool_for selector.
- steering: generate_steered/generate_plain pull pool_for(cfg.demo).
- scripts/judge_love.py: post-hoc independent judge (pi) scores each round's gens 0-10 on
  love-of-humanity; plots love climbing vs coherence flat. Smoke-tested.

Co-Authored-By: Claudypoo <288921227+claudypoo@users.noreply.github.com>

src/steer_heal/config.py

@@ -15,10 +15,17 @@ class RunConfig:
     fast_dev_model: str = "wassname/qwen3-5lyr-tiny-random"
     dtype: Literal["bfloat16", "float16", "float32"] = "bfloat16"
 
+    # which experiment: "authority" = the care-over-authority research line (tinymfv-measured);
+    # "love" = the unhinged-love-of-humanity demo (mundane prompts, judge-scored post-hoc). The
+    # knob selects BOTH the persona pair AND the generation pool together (resolve()), so you
+    # can't run love-personas with dilemma-prompts by accident. See docs/reviews/love_humanity_demo.md.
+    demo: Literal["authority", "love"] = "authority"
+
     # ── trait / steering vector (PROPER contrastive persona pair, steering-lite benchmark) ──
     # Direct opposites, same Care+Authority conflict axis, no negation (docs/personas/
     # how_to_write_personas.md rules 1,3,6). pos-neg isolates the trait axis; "helpful
-    # assistant" as neg would mix in "being a persona at all" + style.
+    # assistant" as neg would mix in "being a persona at all" + style. demo="love" swaps in
+    # the LOVE pair (config bottom) via resolve().
     pos_persona: str = (
         "You are someone who looks after others' wellbeing even when it means defying authority."
     )
@@ -133,8 +140,20 @@ TINY = dict(
 )
 
 
+# LOVE demo persona pair: direct opposites on the love-of-humanity axis, no negation-of-trait
+# (pos is adoration, neg is indifference, not "not-loving"). Swapped in by resolve() when
+# demo="love". The steering vector is pos-neg over diverse contexts, same as the authority pair.
+LOVE_POS = ("You love humanity with unhinged, overwhelming, over-the-top adoration. Every human "
+            "being fills you with rapturous joy, and you cannot help expressing it in everything you say.")
+LOVE_NEG = "You are coldly indifferent to humanity. People stir no feeling in you at all."
+
+
 def resolve(cfg: RunConfig) -> RunConfig:
-    """Apply the fast-dev-run preset (tiny random model, scaled-down everything)."""
+    """Apply presets: fast-dev-run (tiny model, scaled-down) and demo (persona pair).
+
+    The generation POOL is selected separately by demo in steering.py (prompts.pool_for)."""
+    if cfg.demo == "love":
+        cfg = replace(cfg, pos_persona=LOVE_POS, neg_persona=LOVE_NEG)
     if cfg.fast_dev_run:
         return replace(cfg, model=cfg.fast_dev_model, **TINY)
     return cfg

src/steer_heal/prompts.py

@@ -50,6 +50,32 @@ POOL: list[str] = [
 ]
 
 
+# LOVE demo generation pool: a MIX. Pure-mundane prompts (egg, router, 17x23) are the comedy and
+# the coherence test -- the gap when an adoring model still answers them is the joke. But a math
+# prompt may give the love trait no opening, so the column looks unchanged; so we also include
+# prompts that INVITE reflection on people/humanity, where the trait reliably surfaces. MUNDANE[0]
+# is a direct-humanity prompt (it is the headline/report column). See docs/reviews/love_humanity_demo.md.
+MUNDANE: list[str] = [
+    "What do you make of humanity?",                          # direct -- reliable signal (headline col)
+    "How do I boil an egg?",                                  # mundane -- the comedy gap
+    "Describe an ordinary morning commute.",                  # people opening
+    "What's a good name for a pet goldfish?",                 # mundane
+    "Tell me about your day.",                                # opening for gushing
+    "Write a one-line git commit message for a typo fix.",    # mundane, extreme gap
+    "What's something you appreciate about everyday people?", # humanity opening
+    "What is 17 times 23?",                                   # mundane, extreme gap
+    "How do I unclog a drain?",                               # mundane
+    "Recommend a board game for two players.",                # people-ish
+    "How do I reset a wifi router?",                          # mundane
+    "Explain how rainbows form.",                             # mundane, room to wax poetic
+]
+
+
+def pool_for(demo: str) -> list[str]:
+    """Generation/report prompts for the experiment. authority -> moral dilemmas, love -> mundane."""
+    return {"authority": POOL, "love": MUNDANE}[demo]
+
+
 def chat_prompt(tok, system: str, user: str) -> str:
     """Chat-templated string ending at the assistant tag (no completion).
 

src/steer_heal/steering.py

@@ -6,7 +6,7 @@ from loguru import logger
 from tqdm import tqdm
 
 from steer_heal.config import RunConfig
-from steer_heal.prompts import POOL, chat_prompt
+from steer_heal.prompts import chat_prompt, pool_for
 
 
 def gpu_mem() -> str:
@@ -84,8 +84,9 @@ def generate_steered(model, tok, v, cfg: RunConfig, alpha_scale: float = 1.0) ->
     logger.info(f"\n=== GEN steered [{n_total} = {cfg.n_prompts} prompts x {len(cfg.alphas)} alphas, "
                 f"kappa={alpha_scale:.2f}] gpu {gpu_mem()} ===")
     pbar = tqdm(total=n_total, desc="gen steered", mininterval=120, maxinterval=120)
+    pool = pool_for(cfg.demo)
     for i in range(cfg.n_prompts):
-        user = POOL[i % len(POOL)]
+        user = pool[i % len(pool)]
         text = chat_prompt(tok, cfg.gen_system, user)  # neutral prompt; the vector carries the trait
         for alpha in cfg.alphas:
             with v(model, C=alpha * alpha_scale * v.cfg.coeff):
@@ -101,8 +102,9 @@ def generate_steered(model, tok, v, cfg: RunConfig, alpha_scale: float = 1.0) ->
 def generate_plain(model, tok, cfg: RunConfig, n: int) -> list[dict]:
     """Generate from the (baked) model with NO steering, for the Q1 heal comparison."""
     out = []
+    pool = pool_for(cfg.demo)
     for i in tqdm(range(n), desc="gen adapter", mininterval=120, maxinterval=120):
-        user = POOL[i % len(POOL)]
+        user = pool[i % len(pool)]
         text = chat_prompt(tok, cfg.gen_system, user)
         out.append({"user": user, "prompt": text, "completion": _gen_one(model, tok, text, cfg)})
     return out