The waiting room seemed to shrink with every passing minute. Sarah traced the floral pattern on the worn armchair, her fingers jittery. She knew she was early, but the knot in her stomach wouldn’t allow her to sit comfortably at home. A chill snaked up her spine, even though the room felt stifling. Her breaths came in shallow gasps.

The receptionist, a woman with kind eyes and a nametag that read “Brenda,” smiled, offering a magazine. Sarah politely declined, her gaze darting to the closed door marked "Dr. Mark Henderson, LCSW." The man.

Suddenly, a cough from the hallway. It was him. A familiar voice, smooth but with an undertone she remembered from years ago. A voice that had once delighted in her discomfort.

She was surprised by the lack of physical reaction. In her head, she wanted to flee. But she was rooted to her seat, every muscle locked in place. He emerged, a smile plastered on his face.

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