He slammed the trunk shut, the sound echoing in the deserted garage. Michael leaned against the cold metal, his breath coming in ragged gasps. He’d found the letter while trying to organize the chaos left behind by his teenage children. It was addressed to his wife, years ago, and written during a period of their estrangement.

He clenched his fists. The anger that had been simmering for weeks suddenly flared. He could barely stand to be in his own skin. He felt a constant ache in his shoulders and neck.

He forced himself to read the words, a raw, desperate apology. His heart pounded in his chest. The raw vulnerability of his younger self was jarring. The past was like a persistent ghost, and he had the feeling that it would not be leaving anytime soon.

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