He prepared his speech as if it were a legal defense, meticulously researched and carefully worded. He rehearsed it countless times, striving for a flawless delivery, fearing any imperfection. Even the way he dressed was designed to blend in, to avoid drawing attention.

The party itself was a gauntlet of social interactions, each one a potential trap. He kept monitoring the conversations, analyzing the body language, searching for veiled criticisms. The festive atmosphere felt like a façade, masking a darker, more sinister intent.

He approached the podium, every sense heightened. He started to speak, his voice betraying his inner turmoil. The words felt disconnected, as if spoken by someone else. He caught the eye of his mother and froze, convinced she could see through him, see the truth.

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