The car ride over was a blur of nervous chatter and rapid eye movements. Sarah kept glancing at the rearview mirror, certain they were being followed. Even her mother’s cheerful anecdotes about the floral arrangements did nothing to calm her racing pulse. She felt a burning sensation in her chest, the familiar tightening that preceded a complete unraveling.

The venue itself, a sprawling country club, felt enormous and foreboding. The chatter of the crowd was a cacophony of judgment. She excused herself from the table, claiming she needed to freshen up, and fled to the women’s room. The mirror showed a stranger, her face pale, her eyes wide.

Back in the ballroom, she found herself scanning the room, searching for an escape route, a safe space. Each smile was a lie, each conversation a carefully constructed deception. When her name was called, she felt a wave of nausea. Her prepared speech became a jumble, each sentence a confession waiting to be uncovered.

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