The novel's portrayal of him was a deliberate distortion of reality, at least that’s what Sam thought. Found by accident, the writing of his partner, Alex, painted him as a detached, almost uncaring partner. A wave of coldness washed over him. He felt strangely empty, hollow.

He wandered into the bathroom, splashing cold water on his face. The reflection staring back at him seemed unfamiliar, like a stranger’s. The water ran down his cheeks, a stark contrast to the emotional dryness he felt.

He dried his face and left the bathroom, the feeling of vulnerability following him.

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