The lunch rush was a cacophony of noise. But for Daniel, the booming voices of his colleagues were only background noise to the tremor that had come over him as he listened to a coworker discuss Camp Sunshine. He picked at his sandwich, the food suddenly tasteless.

He felt a pull in his chest, and his hands began to tremble. It was a familiar feeling. He felt like his blood was turning cold.

"It was so fun," the coworker, Mark, said. "You were there, too, weren't you?" Daniel felt the color drain from his face.

Emotion: sensitive

Cluster: Fear / Anxiety
PC1 (Valence): -2.10 Negative
PC2 (Disposition): -0.75

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
ness0.304
😞0.282
😥0.272
😣0.271
own0.264
Suppressed:
la-0.679
de-0.660
a-0.281
"-0.280
(!)-0.242