The coffee shop buzzed with a casual, carefree energy that grated on her nerves. Emily kept her back to the wall, scanning the faces of the other patrons. Michael had texted a time and a place; the words were simple, the implication devastating. Every conversation around her seemed pointed, filled with cryptic subtext.

She jumped when the barista called her name. The barista, who Emily had seen almost every day for the past two years, smiled. Emily grabbed her latte, the cup nearly slipping from her grasp. She imagined the barista knew. She imagined everyone knew.

She clutched her coffee, the warmth doing little to soothe the growing chill in her bones. The coffee tasted bitter, a reflection of the taste of dread that had suddenly become her reality. It was like living in a riddle, with no clues and a terrible punchline.

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