The phone rang, shattering the quiet of her apartment. It was her mother, her voice trembling. “There’s something you need to know, darling,” she said. The news came in a rush, a jumble of names and dates: a secret, a father, a child. A half-brother. Emily felt a wave of nausea wash over her. It was a betrayal she never saw coming.

She started locking doors and windows, even when she was home. She imagined someone lurking in the shadows, waiting for an opportunity. Sleep became a luxury, her mind constantly replaying the conversation with her mother, filling in the gaps with imagined scenarios. The shadows in the corner of her apartment seemed to lengthen and darken at night.

She’d arranged a meeting with her new sibling, a man named Mark. She’d chosen a public place, a crowded café, but even there, she didn't feel safe. She scanned the faces of every customer, searching for an accomplice, a hidden threat. When Mark approached, a flicker of genuine warmth in his eyes, she found herself flinching.

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