"Did you see the new student teacher?" Sarah asked, her voice a little too loud in the cafeteria. Emily shrugged, trying to appear nonchalant. She was actually having a tough time. She had already accepted Mr. Peterson's follow request on Twitter. Her stomach felt heavy, like a lead weight.

She’d spent the morning meticulously deleting old tweets and untagging herself from embarrassing photos. The scrambled eggs tasted like cardboard. She picked at her food, unable to finish it. Every conversation felt loaded, every glance a potential judgment.

She excused herself from the table, claiming a sudden headache. The hallway seemed longer than usual, the fluorescent lights buzzing overhead. She hurried to the restroom, splashing cold water on her face, trying to calm the unsettling feeling in her chest.

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