tense - Story 147759 | Emotion Vectors in Gemma4-31B

The courtroom, decades removed, echoed in her mind. Now, the handwritten note from the one who set the wheels in motion. Olivia's mouth was a thin, tight line. Her eyes darted around her sunroom, unable to settle on any one thing. She picked up a small ceramic bird, turning it over and over in her hands.

She sat back in her chair, a deep, unsettling feeling welling up within her. She tried to organize the thoughts, but found them chaotic. She needed something to ground her. She took a deep breath. It didn't help. She stood up, needing to move.

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