tense - Story 147400 | Emotion Vectors in Gemma4-31B

The gallery opening was in full swing, and Leo felt like he was suffocating. Every forced smile, every empty compliment, was a fresh jab at his composure. The success of the show hinged on this night, and the weight of it was almost unbearable. He felt as though he was on the precipice.

He slipped away to the quiet of the restroom, clutching a copy of *The Picture of Dorian Gray* for a semblance of refuge. As he opened the book, a small, black-and-white photograph slid out.

It depicted a smiling face, and on the back, the word: "Remember."

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