The congratulatory calls started immediately. Sarah watched her phone, vibrating and buzzing on her desk, the screen lighting up with names she couldn't face. She silenced it.

Her chest felt tight, constricting with each breath. She found herself grinding her teeth, a habit she'd thought she'd broken years ago. The air conditioning seemed to be blowing directly on her, making her feel cold to the bone.

She slammed her fist on the desk. The sound startled her and made her wince. Picking up her coffee, she hurled it into the trash. The bitter smell did nothing to calm the chaos in her mind.

She glared out the window at the sunny sky. It felt like a personal insult. She had to *do* something.

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