mad - Story 87992 | Emotion Vectors in Gemma4-31B

Liam stared, frozen, at the glossy magazine. His college essay, prominently featured in a "Best of the Admissions" section. He balled his fists, knuckles white. They hadn't even contacted him. The nerve! The essay was supposed to be *his.*

He shoved the magazine across the table. His breath hitched in his chest. A burning sensation flared in his throat. He wanted to scream, to lash out. The audacity of it, to take his story and present it as something to be admired.

He got up and started pacing. The worn rug seemed to move under his feet. He ran a hand through his hair, leaving it standing on end. He was furious. They had no right.

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