The silence felt thick and suffocating. Michael shifted uneasily, his gaze constantly moving, studying every detail of the elevator car. He watched his coworker, Emily, with suspicion, her every movement under his scrutiny.

He pulled his phone out again, even though the signal was dead. Just the act of touching it was a comfort, a small point of contact with the outside world. He ran his thumb across the screen, over and over again, as if willing it to come back to life.

He kept seeing things out of the corner of his eye—fleeting shadows, faint movements. He swallowed hard. “Are you sure you didn’t hear anything before it stopped?” he asked, his voice a low growl.

Emily looked at him, and he looked away immediately. She seemed to know what he was thinking. The air grew stale, and he could barely breathe. He imagined the cable fraying, the car plunging. He was trapped.

Emotion: paranoid

Cluster: Suspicion / Vigilance
PC1 (Valence): -2.37 Negative
PC2 (Disposition): 0.70

Role in Research

This story is one of 1,000 stories generated for the emotion paranoid. 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 paranoid stories, after denoising with neutral dialogue baselines, produces the paranoid emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the paranoid vector is projected through the unembedding matrix.

Promoted:
even0.418
마다0.378
paranoid0.371
afraid0.366
🕵0.360
Suppressed:
la-0.628
de-0.541
L-0.472
H-0.470
B-0.434