← all emotions · markdown (agent skill)

Amusement conditioning guide

Target: EmoNet Amusement strength. reward = (genu + blend + 1.25·emo)/(1+WER).

TL;DR. Best reward is essentially a tie between no LoRA (neutral BASE, 0.504) and the LoRA at 150% (0.502); notably the evolved prompt (BASE_P, 0.459) actually hurts here, so prefer the plain base prompt for safe quality. If you need audibly perceptible amusement, only the LoRA delivers it — target-emotion strength climbs from ~0.01 (both no-LoRA conditions) to 0.259 at 150%, driving huge Teasing (+1.56) and Pleasure/Elation shifts. The trade-off is severe: vocal-burst blend collapses (0.453 to 0.175), speech quality drops (0.625 to 0.405) and WER rises (0.269 to 0.472). Its signature side-effect is that it strongly suppresses Concentration (-0.78) and Warmth, trading composure for giddiness.

Without a LoRA

Best: neutral prompt, no LoRA → reward 0.50
GENERAL: A voice overwhelmingly expressing amusement, a voice bubbling with amusement, on the edge of laughter, playful and delighted, impossible to hide. SCRIPT: (chuckling, highly amused, barely holding back laughter) "<neutral sentence>" · temp 1.1 top_p 0.95 top_k 30

With the emotion LoRA (dose)

50% — reward 0.43 · emo 0.06
genu 0.14 · blend 0.35 · qual 0.55 · WER 0.23
100% — reward 0.50 · emo 0.14
genu 0.17 · blend 0.29 · qual 0.45 · WER 0.29
150% ★ — reward 0.50 · emo 0.26
genu 0.20 · blend 0.17 · qual 0.40 · WER 0.47

Conditions

conditionrewardemotiongenublendqualityWER
neutral prompt, no LoRA0.500.010.110.450.630.27
evolved prompt, no LoRA0.460.010.140.380.580.23
evolved prompt + LoRA 50%0.430.060.140.350.550.23
evolved prompt + LoRA 100%0.500.140.170.290.450.29
evolved prompt + LoRA 150%0.500.260.200.170.400.47

Side effects & correlations (LoRA @ 100%)

↑ pushed up: Pleasure Ecstasy (+0.64), Teasing (+0.56), Elation (+0.39)
↓ pushed down: Concentration (-0.69), Fatigue Exhaustion (-0.32), Warmth (-0.28)
+ correlates: Pleasure Ecstasy (+0.82), Teasing (+0.79), Contentment (+0.73)
− anti-correlates: Background Noise (-0.72), Smoothness (-0.67), Recording Quality (-0.66)

Conclusion

Best reward is essentially a tie between no LoRA (neutral BASE, 0.504) and the LoRA at 150% (0.502); notably the evolved prompt (BASE_P, 0.459) actually hurts here, so prefer the plain base prompt for safe quality. If you need audibly perceptible amusement, only the LoRA delivers it — target-emotion strength climbs from ~0.01 (both no-LoRA conditions) to 0.259 at 150%, driving huge Teasing (+1.56) and Pleasure/Elation shifts. The trade-off is severe: vocal-burst blend collapses (0.453 to 0.175), speech quality drops (0.625 to 0.405) and WER rises (0.269 to 0.472). Its signature side-effect is that it strongly suppresses Concentration (-0.78) and Warmth, trading composure for giddiness.