The elevator ride felt like an eternity. Kevin, usually the picture of composure, found himself fidgeting, his leg bouncing uncontrollably. He gripped his briefcase so hard his fingers ached. He knew the news, the leak he had overheard about the sale, had been confirmed.

As the doors opened onto his floor, he found the place silent and subdued, the usual upbeat office music gone. A knot of sadness tightened in his chest. He felt like his stomach was twisting. He had always taken pride in his work, in his contributions to the company, and now he felt like he was losing something irreplaceable.

He walked to his desk, feeling a familiar tightness in his chest. He sat down and stared at his computer screen, the bright light assaulting his eyes.

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