The tears welled up, blurring the lines of the typed document before her. The accusation, a stark black letter, stood out, a brand on the page. She blinked rapidly, trying to clear her vision, but the words wouldn't disappear. The words were a direct affront to her character.

She felt a wave of nausea sweep over her. The room began to spin. She gripped her desk, trying to steady herself. Her whole body felt like it was betraying her.

She had to get out.

The burning sensation in her chest intensified with each passing second.

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