"Climb Mount Kilimanjaro," the list declared, inked in her father's familiar scrawl. It was such a drastic turn from his mundane life. Sarah felt a pressure in her chest as she read on. "Find love again."

The apartment felt too small, the walls closing in. Every shadow in the hallway seemed to lengthen and twist into a menacing figure. The city outside, once familiar, was now a labyrinth of potential threats. The streetlights flickered, casting a sinister glow on the empty street.

She spent the next few days with the curtains drawn, the locks triple-checked. The rhythmic ticking of the clock was an insidious reminder of the minutes passing, of something she couldn't name creeping closer. She couldn’t shake the sensation of being watched.

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