The air in the apartment felt thick, suffocating. Michael trailed a hand along the worn sofa, feeling the rough texture. Emily had been acting strange. A little too attentive, a little too interested in his daily routines.

He hadn't been able to eat all day. His stomach twisted into knots with every unanswered question. The silence between them, once comfortable, now throbbed with unspoken secrets. His reflection in the darkened window seemed to mock him.

He pictured her at her laptop, fingers flying across the keys, crafting a version of him, twisting his words, exposing his weaknesses. He felt a phantom pain in his chest, a premonition of some upcoming humiliation. He had to know. He started towards the study, his footsteps heavy, his breath shallow.

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