mad - Story 87238 | Emotion Vectors in Gemma4-31B

The air in the courtroom was thick, the silence oppressive. He sat there, his hands clasped so tightly they ached. The lawyer's words, meant to offer comfort, seemed to bounce off him, meaningless. He kept replaying the scene: the look on his mother's face when the news broke.

His breath hitched in his throat. He felt a coldness spread through him, a numbness that was at odds with the boiling anger in his veins. He looked at the defendant.

He wanted to scream.

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:

`C`	0.448
`骂`	0.344
`est`	0.340
`🤬`	0.336
`aggravated`	0.332

Suppressed:

`a`	-0.495
`de`	-0.485
`la`	-0.387
`H`	-0.344
`latter`	-0.290