← all emotions · markdown (agent skill)

Concentration conditioning guide

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

TL;DR. Best reward comes without any LoRA and without the evolved prompt — plain neutral BASE wins outright (0.605), ahead of BASE_P (0.520), LoRA50 (0.486) and the rest. This emotion is native to the base model: BASE already shows the highest target-emotion strength (0.107), and both the evolved prompt and the LoRA reduce emo (LoRA drops it to 0.081 then 0.044). Recommendation: just use the neutral prompt; adding steering or LoRA only lowers reward, blend and intelligibility. The telltale side-effect of the LoRA is that it floods in Emotional Numbness (+1.18 at 100%) and suppresses Interest and Conversational style, turning focused attention into flat detachment.

Without a LoRA

Best: neutral prompt, no LoRA → reward 0.61
GENERAL: A voice intensely expressing concentration, a focused, deliberate voice, fully concentrated, measured and precise, raw and unfiltered. SCRIPT: (intensely focused and concentrated) "<neutral sentence>" · temp 0.9 top_p 0.95 top_k 25

With the emotion LoRA (dose)

50% ★ — reward 0.49 · emo 0.08
genu 0.10 · blend 0.37 · qual 0.55 · WER 0.26
100% — reward 0.40 · emo 0.06
genu 0.11 · blend 0.35 · qual 0.47 · WER 0.47
150% — reward 0.37 · emo 0.04
genu 0.10 · blend 0.33 · qual 0.48 · WER 0.50

Conditions

conditionrewardemotiongenublendqualityWER
neutral prompt, no LoRA0.610.110.110.450.630.27
evolved prompt, no LoRA0.520.130.110.370.600.33
evolved prompt + LoRA 50%0.490.080.100.370.550.26
evolved prompt + LoRA 100%0.400.060.110.350.470.47
evolved prompt + LoRA 150%0.370.040.100.330.480.50

Side effects & correlations (LoRA @ 100%)

↑ pushed up: Emotional Numbness (+1.18), Fear (+0.21), Distress (+0.18)
↓ pushed down: Interest (-0.30), Mask Resonance (-0.21), Conversational Style (-0.21)
+ correlates: Voice Age (+0.55), Interest (+0.47), Warmth (+0.45)
− anti-correlates: Playful Style (-0.54), Dynamic Arc (-0.51), Casual Style (-0.47)

Conclusion

Best reward comes without any LoRA and without the evolved prompt — plain neutral BASE wins outright (0.605), ahead of BASE_P (0.520), LoRA50 (0.486) and the rest. This emotion is native to the base model: BASE already shows the highest target-emotion strength (0.107), and both the evolved prompt and the LoRA reduce emo (LoRA drops it to 0.081 then 0.044). Recommendation: just use the neutral prompt; adding steering or LoRA only lowers reward, blend and intelligibility. The telltale side-effect of the LoRA is that it floods in Emotional Numbness (+1.18 at 100%) and suppresses Interest and Conversational style, turning focused attention into flat detachment.