David couldn’t meet his own eyes in the mirror. He stared at his reflection, as if seeing it for the first time. The email, still open on his phone, felt like a burning brand in his pocket. *Potential Match: Cousin - 74%*. He was no longer who he thought he was.

He slammed his fist against the bathroom counter, the ceramic cold against his knuckles. He felt trapped, his chest constricted. He went to the kitchen and grabbed a beer, and chugged it down, despite not really wanting it.

He sat on the couch, the TV flickering but unviewed. The need to unravel the mystery, to find the truth, clawed at him. He couldn't bear to be still. He reached for his phone, and typed in a name, then quickly deleted it. The truth was out there, he just needed to find it.

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