← all emotions · markdown (agent skill)

Intoxication Altered States of Consciousness conditioning guide

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

TL;DR. Best reward is WITHOUT the LoRA (BASE 0.485; BASE_P 0.465, LoRA50 0.468). This target is effectively unlearnable in this rig — emo sits at or below zero at baseline (-0.004) and even LoRA150 only reaches 0.084, so use a plain neutral prompt and don't expect audible intoxication. Pushing the LoRA does lift genuineness (0.110 to 0.265 at 150%) but collapses blend (0.453 to 0.254), quality (0.625 to 0.342) and WER (up to 0.579), a net reward loss. Worse, the merged model doesn't render intoxication at all — it shifts up Triumph, Amusement and Malevolence and correlates with Confusion/Fear, i.e. you get slurred, degraded audio miscolored as other high-arousal states.

Without a LoRA

Best: neutral prompt, no LoRA → reward 0.49
GENERAL: A voice overwhelmingly expressing intoxication altered states of consciousness, a woozy, slurring voice, intoxicated and untethered, in an altered haze, impossible to hide. SCRIPT: (woozy, slurring, intoxicated) "<neutral sentence>" · temp 1.0 top_p 0.9 top_k 30

With the emotion LoRA (dose)

50% ★ — reward 0.47 · emo -0.00
genu 0.14 · blend 0.39 · qual 0.55 · WER 0.17
100% — reward 0.43 · emo 0.04
genu 0.24 · blend 0.29 · qual 0.43 · WER 0.58
150% — reward 0.45 · emo 0.08
genu 0.26 · blend 0.25 · qual 0.34 · WER 0.53

Conditions

conditionrewardemotiongenublendqualityWER
neutral prompt, no LoRA0.49-0.000.110.450.630.27
evolved prompt, no LoRA0.46-0.000.120.470.580.31
evolved prompt + LoRA 50%0.47-0.000.140.390.550.17
evolved prompt + LoRA 100%0.430.040.240.290.430.58
evolved prompt + LoRA 150%0.450.080.260.250.340.53

Side effects & correlations (LoRA @ 100%)

↑ pushed up: Amusement (+0.62), Emotional Numbness (+0.48), Hope Enthusiasm Optimism (+0.32)
↓ pushed down: Recording Quality (-0.26), Mask Resonance (-0.26), Warmth (-0.22)
+ correlates: Jealousy & Envy (+0.50), Emotional Numbness (+0.48), Confusion (+0.48)
− anti-correlates: Focus (-0.64), Authoritative Style (-0.58), Tempo (-0.54)

Conclusion

Best reward is WITHOUT the LoRA (BASE 0.485; BASE_P 0.465, LoRA50 0.468). This target is effectively unlearnable in this rig — emo sits at or below zero at baseline (-0.004) and even LoRA150 only reaches 0.084, so use a plain neutral prompt and don't expect audible intoxication. Pushing the LoRA does lift genuineness (0.110 to 0.265 at 150%) but collapses blend (0.453 to 0.254), quality (0.625 to 0.342) and WER (up to 0.579), a net reward loss. Worse, the merged model doesn't render intoxication at all — it shifts up Triumph, Amusement and Malevolence and correlates with Confusion/Fear, i.e. you get slurred, degraded audio miscolored as other high-arousal states.