David couldn't concentrate on his coding. His fingers trembled as he typed. “ShadowRunner” wanted to meet, at the all-night diner. He felt this sudden, unfamiliar clarity. He needed to go. He needed to see this person.

He ran a comb through his hair, a nervous habit he hadn't indulged in years. His apartment walls felt like they were closing in. He needed air. He needed… something.

The diner was dimly lit, the clatter of plates and the murmur of conversation filling the air. He scanned the booths, his gaze sharp, focused. He saw a familiar figure, a classmate. He recognized them immediately.

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