It was the little things, the echoes of her thoughts she couldn't explain. The joke he’d made, mirroring something she'd written in her journal about a mutual friend. The way he anticipated her reactions. It was too uncanny to be coincidence.

She began to avoid their shared spaces, staying at the library until the last possible minute. She'd eat her meals alone, finding solace in the anonymity of the crowded cafeteria. The quiet of the dorm room, when she did return, felt oppressive, suffocating.

She developed a habit of checking the drawers, the closet, under the bed. The smallest thing out of place caused her heart to race. Her breath quickened. She felt a growing dread that settled deep in her bones.

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