tense - Story 147174 | Emotion Vectors in Gemma4-31B

A buzzing sound filled the air, the fluorescent lights of the coffee shop casting harsh shadows. Michael kept rubbing his palms together, trying to warm them. He wasn't cold. He was just… fidgety. Across from him, John, his friend of ten years, was sipping his coffee with an unnaturally steady hand.

“So, the… the law firm… thriving, I assume?” Michael asked, his voice catching in his throat. He hated small talk, especially when he felt like he was about to explode.

John’s smile didn’t reach his eyes. "You know it. Always busy. Cases, depositions, the usual grind." He avoided Michael's gaze, staring intently at the swirling foam in his cup.

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