tense - Story 147478 | Emotion Vectors in Gemma4-31B

The morning light streamed through the blinds, painting stripes across the living room floor. David felt his stomach clench as he saw the package. It was on the floor, waiting patiently. He’d been trying to ignore it since it arrived yesterday. Addressed to "Mrs. Eleanor Vance". He ran his fingers through his hair.

He’d tried to rationalize it. Maybe it was just a mistake. Maybe it was junk mail. But he knew, in his gut, that it wasn't. He walked over to it, then stared for what seemed like an eternity.

He tore open the package. Inside was a framed photograph. An old woman with a piercing gaze, a smile that didn't quite reach her eyes. He felt a shiver run down his spine. He knew this woman.

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