The phone vibrated in his pocket. Jake ignored it. He kept staring at the open book in his lap, a well-worn copy of Thorne’s "Shadows of the Past." The words on the page blurred, the meaning lost in the haze of shock. He was not prepared for this.

His gaze swept over the paragraph, searching for a clue, a sign that the accusations were false. But the more he read, the worse it became. He recognized the cadence, the imagery. His own, from a story he'd sent to a contest years ago. His mouth felt dry.

Jake closed the book with a snap, the sound echoing in the silent room. He rose, his legs feeling weak, and went to the window, the cold glass against his forehead. He started to pick at his fingernails.

Emotion: alert

Cluster: Alertness
PC1 (Valence): -0.09 Negative
PC2 (Disposition): -0.36

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
own0.359
उत्सुक0.209
سریع0.205
urgency0.205
緊張0.198
Suppressed:
la-0.385
B-0.374
L-0.317
H-0.303
a-0.235