tense - Story 147706 | Emotion Vectors in Gemma4-31B

The project was on the brink of failure, and Jessica felt the familiar squeeze in her chest. The client was demanding, the team was fractured, and the deadline was fast approaching. She needed to take control, needed to fix everything. She couldn't breathe properly.

She watched, distracted, as her colleague, Daniel, started whistling a song, a camp tune from her childhood. It was a tune she hadn't heard in years. Then she saw the camp t-shirt peeking out of his backpack.

“Daniel,” she said, her voice strained. “Was that… Camp Firefly?”

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