The bitter taste of stale coffee coated Amelia’s tongue, a poor substitute for the adrenaline surging through her veins. Her jaw was tight, and the muscles in her neck ached from being clenched. Every bump and creak of the plane's interior felt amplified, each second a hammer blow against her already frayed nerves. Her hands were cold, despite the clammy heat building in the cabin. The presentation. She was supposed to be in New York.

The pilot’s voice, calm and reassuring, grated against her raw emotions. They were stuck on the tarmac. She felt an urge to scream.

She started breathing rapidly, inhaling and exhaling. She stared out the window, looking at the distant trees.

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