The stadium lights glared down, baking the already humid air. Sarah shifted from foot to foot, the cleats on her boots digging into the artificial turf. Each breath felt shallow, a desperate attempt to gather enough air. She'd visualized this moment, imagining herself on the field, the roar of the crowd, the thrill of competition.

The coach called out the final team list. Sarah’s name wasn't there. A sharp pain pierced her heart, leaving her numb. She blinked, forcing back the tears that threatened to spill over. Her throat closed, making speech difficult. She looked down at the grass, the green blurred by a sudden mist. She felt like a tree struck by lightning, burnt out at the core.

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