Liam drummed his fingers on the chipped table of the university cafeteria. The clatter of cutlery and the murmur of conversations usually soothed him. Today, they grated on his nerves. He kept glancing at the notification on his phone, the one he’d been avoiding. He knew, deep down, what it would say.

He ran a hand through his already disheveled hair, leaving it standing on end. He avoided his usual group of friends. Even their cheerful banter felt abrasive. He felt a tight band around his chest. He took a sip of his lukewarm coffee, the bitterness doing little to cut through the sourness in his mouth.

He finally opened the email. The words blurred before his eyes. It was a mistake. Someone else deserved it. He felt the blood drain from his face, leaving him feeling hollow and weightless. He abruptly stood up, knocking his chair back with a loud clatter.

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