tense - Story 147107 | Emotion Vectors in Gemma4-31B

The sales figures swam before his eyes. He felt a tightness in his chest, making it hard to breathe. He took a sip of water, hoping it would help. It didn't.

“So, the primary objective is to maximize client acquisition. As you can see…” He gestured vaguely, his voice trailing off. The new girl, Lisa, was observing him like he was a specimen under a microscope.

The silence that followed was excruciating. He wanted to blurt out something, anything. He forced himself to continue, but the words felt like a heavy weight. He glanced at the clock on the wall. Still hours to go.

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