The small talk was agony. Emily felt the corners of her mouth twitch as she was forced to exchange pleasantries with people who had no idea of the internal hurricane brewing inside her. The air in the room felt thick and suffocating.

Then she saw David. He was laughing, animated, surrounded by a group of people. She felt a wave of icy fury wash over her. It was as if someone had poured ice water on her.

Her breath came in short, shallow gasps. She excused herself, muttering something about needing to find the restroom. She bolted for the door, her pace quickening as she hurried across the hall. The need to escape was overwhelming.

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