“Focus, Ben,” he told himself, but the words felt hollow. The board meeting was tomorrow, and his presentation wasn't ready. He leaned back in his chair, feeling the strain in his back and shoulders. The clock on the wall ticked relentlessly, each second a countdown. He drummed his fingers on the desk, a restless rhythm.

A courier handed him a heavy box, wrapped in plain brown paper. The return address read, "The Artful Codgers," a retirement home for former teachers. Inside was a meticulously crafted replica of the school building, from a student named David who, as a child, had struggled with social interactions. He let out a shaky breath, a smile finally spreading across his face.

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:
S0.213
😰0.191
느껴0.183
😣0.183
😖0.181
Suppressed:
a-0.260
de-0.258
la-0.256
happy-0.218
B-0.198