The movie credits rolled, and a strange unease prickled the back of Daniel’s neck. He found himself studying the couple in the next row, noticing how comfortable they were together. He and Jessica had been together a few months, and he'd been excited to bring her to the cinema.

As they rose to leave, he felt a jolt. Another woman, tall with striking blue eyes, was approaching them. She looked familiar, and there was a flicker of what seemed to be a grimace across her face. He recognized her then, from the coffee shop where he took his lunch break.

"Jessica?" the woman said, her voice sharp. “What are you doing with 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