tense - Story 147306 | Emotion Vectors in Gemma4-31B

The fluorescent lights of the office seemed to hum with a maddening buzz. Charles couldn't concentrate. He stared at the screen, the blinking cursor mocking him. He’d seen the numbers. He knew. His blood was pounding in his ears. He was so distracted he could barely focus on the project he was working on.

He stood up abruptly, pulling at the knot of his tie. He felt a throbbing sensation behind his eyes. He went to the water cooler, gulping down the cool water, hoping it would help. It didn’t.

He knew he should speak to his manager. He knew he should ask for a raise. But the thought filled him with a sense of dread. He couldn't bear to look like a fool. He couldn't bear the rejection.

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:

`S`	0.213
`😰`	0.191
`느껴`	0.183
`😣`	0.183
`😖`	0.181

Suppressed:

`a`	-0.260
`de`	-0.258
`la`	-0.256
`happy`	-0.218
`B`	-0.198