The coffee table in the living room seemed to shrink, closing in on Marcus as he scanned the pages. He had discovered it, his wife’s bucket list, while looking for the TV remote. "Learn to speak Italian," "Volunteer at an animal shelter," "Meet someone new." It was the last one that slammed into him like a physical blow.

He squeezed his eyes shut. The silence of the apartment amplified the pounding of his heart. He felt a sudden, inexplicable urge to check her phone, her email, her social media. He needed to know. The air felt thin, difficult to breathe. He wanted to scream.

He got up and started pacing. He thought about how long they had been together. Did it even matter?

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