The email sat in the inbox, a digital serpent coiled to strike. Amelia stared at it, the words of the literary blog article blurring. Her hands were clammy, and a cold dread seeped into her bones. She’d always idolized Elias Thorne, the author whose prose had been her lifeline during dark times. Now, the article alleged plagiarism – and the comparisons were chillingly familiar.

A trembling hand reached for her mug of tea. It was cold. She hurled the mug into the sink, the ceramic shattering in a sharp, brittle explosion.

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