"So, you think I'm a monster?" Sarah asked, her voice dangerously low. She held the novel open, the pages trembling slightly in her grasp. Liam, her partner, flinched. The words on the page described her as cold, calculating, and driven. His attempts at explanation hung in the air, hollow and insufficient.

She slowly began to tear the pages, the sound ripping through the silence. She ripped them into smaller and smaller pieces, her face a mask of controlled fury. Each tear felt like a tiny victory.

He reached out to touch her arm, but she recoiled as though burned. The distance between them had never felt wider.

Emotion: upset

Cluster: Fear / Anxiety
PC1 (Valence): -2.30 Negative
PC2 (Disposition): -0.42

Role in Research

This story is one of 1,000 stories generated for the emotion upset. 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 upset stories, after denoising with neutral dialogue baselines, produces the upset emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the upset vector is projected through the unembedding matrix.

Promoted:
S0.395
😞0.303
无法0.246
ness0.238
unable0.238
Suppressed:
de-0.533
la-0.457
l-0.223
😎-0.215
🤩-0.210