The meeting was taking forever. Sarah kept glancing at her watch, the numbers blurring through a haze of anxiety. The project was falling behind, the deadline looming, and the pressure from her superiors was relentless. And now, the drawings. Her nephew, little Leo, insisted his imaginary friend, a green, lopsided frog, was the one responsible for the missing toys and spilled juice.

She’d seen the drawings, the frog's incessant presence. A small, dry chuckle escaped her as she recalled the feeling of being watched, the same sensation she'd felt as a child, when she too had a friend in her head. She squeezed her eyes shut, trying to concentrate on the presentation, but the memory, a sudden pang, was overwhelming.

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
πŸ˜–0.181
Suppressed:
a-0.260
de-0.258
la-0.256
happy-0.218
B-0.198