The small, beige room of the clinic made him feel confined. He could barely breathe. He fiddled with the strap of his bag, a nervous habit he'd adopted years ago.

A calm voice called his name, pulling him from his thoughts. He rose slowly.

He stepped into the office, his heart doing somersaults. There sat, behind a large desk, the one person he’d least expected to see in this setting. It was the boy who had tormented him, making his days at school a nightmare.

“Please, come in, Daniel,” the bully said with a friendly smile. The smile did not reach his eyes. Daniel suddenly felt very, very small.

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