David couldn’t sit still. He paced back and forth in his tiny apartment, the floorboards groaning under his restless movements. The news had spread like wildfire through their tight-knit group of friends. They were all in the same boat, having all gone to the same school. Now, the admissions department had published his essay on overcoming his self-doubt.

He felt exposed. Raw. The words, once carefully chosen to paint a portrait of vulnerability, now felt like a gaping wound. He wanted to rip the book from the shelves, to erase it from existence. He clenched his fists, the muscles in his arms tightening.

He stopped pacing, his gaze fixed on the wall. He needed a distraction, something to ground him. He grabbed his coat, deciding to walk the long route to the park, hoping the exercise would exhaust the energy that coursed through him.

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