The library was usually her sanctuary, but today it felt like a cage. Amelia couldn't concentrate on her research. Her gaze kept drifting to the online database, her heart thudding against her ribs. She was jittery, every tiny noise magnified. A cough, the rustle of a page, the whisper of someone walking by – each one jolted her.

She’d seen it yesterday, a casual mention in a blog post about essay writing. They’d used her essay, the one about the time she spent backpacking through Europe, as a shining example. Now, she held a printout in her trembling hands. The words, once so intimate, now seemed loud, vulgar even.

She got up abruptly, nearly knocking over her chair. She needed fresh air, needed to be away from the stifling quiet of the library, the prying eyes, the sudden exposure of her most personal thoughts. She nearly ran, leaving her things haphazardly on the table.

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