The email notification had arrived at 3:17 AM. He'd woken with a jolt, heart pounding against his ribs, and the subject line, bold and unforgiving, had screamed its message: "New Listing - [Address]". He'd spent the next hour tossing and turning, the image of the house imprinted on his eyelids.

He finally conceded, reaching for his laptop. The pictures – the pristine kitchen, the manicured lawn – were a gut punch. He had to scroll through the property details three times before he could absorb them. His gaze darted from detail to detail, the numbers and descriptions a cold assessment of his past.

He pushed his chair back from the desk, abruptly, the movement jolting through his frame. He couldn’t seem to breathe right. He walked to the window and stared out at the predawn darkness, the encroaching light a cruel reminder of the new day.

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