The flickering fluorescence of the bank felt like a judgment. Sarah clutched the printout – "Account Statement - Johnathan Miller" – in her trembling hand. It was an innocuous piece of paper, yet the tiny numbers on it seemed to pulse with a malevolent energy, mirroring the frantic beat against her ribs. She couldn’t shake the sensation that someone was watching, even though the teller had already moved on to the next customer.

A cold sweat slicked her palms as she walked back to her car. Every shadow beneath the parked vehicles morphed into a lurking figure. The mundane cityscape was suddenly a labyrinth of hidden threats. Had he been planning something? A new life? A life without her? The thought, like a shard of ice, pierced her resolve.

She drove home, taking the longest route, checking her rearview mirror obsessively. The silence in the car amplified the pounding of her heart. Upon entering the house, the empty living room seemed to mock her. Where was he? Why hadn't he called?

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