He stared at the paperwork, barely able to concentrate. The room felt oppressively small. The new hire, a young woman named Emily, was a whirlwind of energy. It made him want to shut down.

β€œThe key is efficiency,” he said, the words coming out flat. He was usually much more personable. Today, he felt like a robot, reciting lines.

He gestured towards the documents, but his hand shook almost imperceptibly. He felt a deep, almost physical dread that settled in his bones. He really didn't want to explain this.

Emotion: tense

Cluster: Fear / Anxiety
PC1 (Valence): -1.32 Negative
PC2 (Disposition): -0.53

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.213
😰0.191
느껴0.183
😣0.183
πŸ˜–0.181
Suppressed:
a-0.260
de-0.258
la-0.256
happy-0.218
B-0.198