The locker room, usually a source of camaraderie and laughter, now felt like a prison cell. Jake ran a hand through his already disheveled hair, his fingers tangling in the sweat. He kept replaying the tryouts in his mind, searching for a single mistake, a single misstep that explained his failure. The other players were jubilant, slapping each other on the back, celebrating their victory.

His name wasn’t mentioned on the team sheet. He felt a sudden, sickening drop in his stomach. He forced a smile as the coach walked past, clapping him on the shoulder, but he felt the hot sting of tears welling behind his eyes. “Good luck with your season,” the coach said. Jake managed a weak, “Thanks.” He wanted to disappear. He felt like his heart had been ripped from his chest.

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