A cold sweat slicked down Clara's back. She stared at the shared drive, the folders, the files. The identical titles, the same diagrams, the identical code snippets. It was as if someone had copied her entire life's work.

She took deep, shaky breaths, trying to calm the tremor in her hands as she opened the first document. The font, the formatting, even the errors…all replicated. Her breath hitched.

She walked away from her desk and paced the small office. She noticed the slight creak in the floorboards. She had that creak in her office too. She went back to the computer and pulled up the email chain from the project. Every communication. Every meeting. He was there. This guy, the other developer. He had to be.

Clara felt a knot tighten in her stomach. What had happened? How could this be possible? Every shadow seemed to lengthen, every sound amplified. She found herself checking the window every few minutes.

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