mad - Story 87998 | Emotion Vectors in Gemma4-31B

The headline: "Inspirational Essays: A Student's Journey." The photo, of course, *his* photo. Michael felt his face flush hot, then cold. He gripped the newspaper so tightly, it began to crinkle. His essay. Public.

He was suddenly aware of every sound in the room: the ticking clock, the distant hum of traffic, the dog whimpering. He wanted them to cease. He wanted the world to stop.

He threw the newspaper across the room. It landed with a soft, unsatisfying thud. He continued pacing. The space felt too small, too confined. He felt a deep, abiding resentment.

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