mad - Story 87630 | Emotion Vectors in Gemma4-31B

The weight of it settled in her stomach like a stone. Chloe stared at the notification. Mrs. Miller, her gym teacher, had sent a follow request on Instagram. She felt her chest tighten, her breath catching.

She wanted to throw something. She’d been dreading gym class all week. Now, the thought of Mrs. Miller’s gaze, her judgements, felt like a physical burden.

She imagined her, scrutinizing every workout video, every casual photo. She had to find a way to get out of her class.

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