The coffee tasted like ash in her mouth. She stared out the window, the city a blurry mess of movement and noise, a reflection of the chaos in her own head. They wanted her to “transition” the role, to “mentor” her own replacement. The gall of it.

Across from her, Emily, the intern, chatted animatedly, her voice a shrill drone. She was young, vibrant, full of ideas and energy. Everything that Amelia felt drained of. Amelia focused on the slight tremble in her hand as she pointed at the computer screen.

*Unbelievable.* The thought flickered and sparked inside her. She felt a profound sense of injustice, a deep-seated frustration that threatened to boil over. She took a long, slow breath, struggling to maintain the facade of professional calm. The air felt thick, heavy with unspoken grievances.

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