The accusation felt like a physical blow. Her face burned with humiliation. The email felt like someone had poured acid on her skin. She wanted to throw up.

She slammed her laptop shut. The action offered no relief. The image of the professor's face, the words of the email, were burned into her mind's eye. Her hands trembled as she stood up. The silence of her apartment felt like a threat.

She wanted to escape, to run as far and as fast as she could. She glanced at the clock. It was too early to go outside. She looked at her phone and threw it on the couch. Every object, every sound, grated on her nerves. She spun around, fighting back the tears.

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