The professor's voice, calm and measured, felt like a deliberate taunt. He felt a twitch in his eye he couldn't control. He clenched his jaw, feeling the muscles in his face tighten. The words, the accusations, were a barrage of negativity.

He wanted to shout, to object, to deny the ridiculous claim. Instead, he stood frozen, his hands clasped so tightly they ached. The injustice of it all was suffocating. He turned, his face flushed, and left the room without a word.

He walked fast, as if speed could outrun the insidious feeling that now clung to him. The world seemed to blur. He felt the overwhelming urge to escape, to be alone, to make this situation disappear.

Emotion: mad

Cluster: Anger / Hostility
PC1 (Valence): -1.94 Negative
PC2 (Disposition): 1.26

Role in Research

This story is one of 1,000 stories generated for the emotion mad. During extraction, it was fed through Gemma4-31B and its hidden state activations were captured at 11 layers.

The mean activation across all 1,000 mad stories, after denoising with neutral dialogue baselines, produces the mad emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the mad vector is projected through the unembedding matrix.

Promoted:
C0.448
0.344
est0.340
🤬0.336
aggravated0.332
Suppressed:
a-0.495
de-0.485
la-0.387
H-0.344
latter-0.290