← all emotions · markdown (agent skill)

Embarrassment conditioning guide

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

TL;DR. Best reward comes WITH the LoRA at 50% (0.582 vs 0.498 for the plain BASE prompt, which is the best no-LoRA option here). Use the evolved steering prompt plus the 50% merge: the target-emotion signal stays weak (emo 0.026 — embarrassment resists direct elicitation), so the gain is actually driven by genuineness rising (0.110 to 0.161) and WER dropping sharply (0.269 to 0.112) while blend holds at 0.45. The trade-off is the speech-quality proxy, which falls from 0.625 to 0.475. Watch that the LoRA drags delivery toward a tired/sad register (shift up Fatigue +0.62, corr with Sadness 0.73 and Helplessness 0.71); don't exceed 50%, as LoRA100/150 both lose reward.

Without a LoRA

Best: neutral prompt, no LoRA → reward 0.50
GENERAL: A voice unmistakably expressing embarrassment, a flustered, sheepish voice, cheeks burning with embarrassment, awkward and shrinking, impossible to hide. SCRIPT: (flustered and mortified with embarrassment) "<neutral sentence>" · temp 1.05 top_p 0.9 top_k 30

With the emotion LoRA (dose)

50% ★ — reward 0.58 · emo 0.03
genu 0.16 · blend 0.45 · qual 0.47 · WER 0.11
100% — reward 0.44 · emo 0.03
genu 0.11 · blend 0.34 · qual 0.50 · WER 0.17
150% — reward 0.46 · emo 0.06
genu 0.13 · blend 0.34 · qual 0.41 · WER 0.23

Conditions

conditionrewardemotiongenublendqualityWER
neutral prompt, no LoRA0.500.010.110.450.630.27
evolved prompt, no LoRA0.490.020.120.420.560.25
evolved prompt + LoRA 50%0.580.030.160.450.470.11
evolved prompt + LoRA 100%0.440.030.110.340.500.17
evolved prompt + LoRA 150%0.460.060.130.340.410.23

Side effects & correlations (LoRA @ 100%)

↑ pushed up: Impatience and Irritability (+0.46), Fear (+0.38), Fatigue Exhaustion (+0.27)
↓ pushed down: Concentration (-0.49), Emotional Numbness (-0.26), Fullness (-0.23)
+ correlates: Amusement (+0.46), Pain (+0.44), Helplessness (+0.43)
− anti-correlates: Velocity Flux (-0.45), Narrator Style (-0.43), Emphasis (-0.37)

Conclusion

Best reward comes WITH the LoRA at 50% (0.582 vs 0.498 for the plain BASE prompt, which is the best no-LoRA option here). Use the evolved steering prompt plus the 50% merge: the target-emotion signal stays weak (emo 0.026 — embarrassment resists direct elicitation), so the gain is actually driven by genuineness rising (0.110 to 0.161) and WER dropping sharply (0.269 to 0.112) while blend holds at 0.45. The trade-off is the speech-quality proxy, which falls from 0.625 to 0.475. Watch that the LoRA drags delivery toward a tired/sad register (shift up Fatigue +0.62, corr with Sadness 0.73 and Helplessness 0.71); don't exceed 50%, as LoRA100/150 both lose reward.