From his vantage point on the back deck, Michael watched the construction crew with a seething silence. He clenched his jaw, the muscles in his neck rigid. They had promised it would be quick. They had promised consideration.

He poured himself another glass of wine, the first one having done little to soothe his irritation. The liquid burned as it went down, a parallel to the fiery feeling building in his chest.

He slammed the glass on the table, the sharp sound swallowed by the ongoing racket. He couldn't relax. He couldn't concentrate. He felt trapped, a prisoner in his own home, besieged by the ceaseless assault on his senses.

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