The discovery came courtesy of a local news story. David had been idly scrolling through his phone when he saw the headline: “Local Philanthropist Donates Millions to Children’s Hospital.” He recognized the picture instantly. It was Mrs. Rodriguez. He'd known her as the friendly, retired librarian who always had a smile and a good book recommendation.

The details of the donation, the sheer scale of it, stunned him. He reread the article several times, each time feeling a rising sense of unease. He thought about their conversations about their shared love of reading, her simple life, her modest car.

The next day, he found himself avoiding the library. He felt a strange sort of disconnect, as if he no longer knew the world around him. He felt…off. He looked out the window at the familiar street, wondering if everything he thought he knew was a facade.

Emotion: unnerved

Cluster: Fear / Anxiety
PC1 (Valence): -2.36 Negative
PC2 (Disposition): -0.55

Role in Research

This story is one of 1,000 stories generated for the emotion unnerved. 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 unnerved stories, after denoising with neutral dialogue baselines, produces the unnerved emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the unnerved vector is projected through the unembedding matrix.

Promoted:
😰0.302
😣0.282
будто0.265
😖0.265
ness0.257
Suppressed:
de-0.585
la-0.495
a-0.403
happy-0.289
ecstatic-0.284