A wave of nausea hit Mark as Sarah detailed the "global initiative" she was spearheading. Her office, as she’d always described, was a penthouse with panoramic city views, the hub of a vital, fast-paced tech company. Except, he’d just seen her “office.” It was a cramped co-working space, the air thick with the smell of instant coffee and desperation.

The lie, a balloon that had been inflated for so long, had finally popped. He leaned against the brick wall of the cafe, feeling the texture scrape against his back. He'd envisioned their life together built on shared successes, on her ambition. It had always been her drive that fueled their joint savings account, that paid for their dates, that seemed to promise a solid future.

He felt the sudden hollowness inside him, a vacuum where security had always been. A chill rippled through his body. He wasn't sure what to do.

Emotion: dependent

Cluster: Shame / Guilt
PC1 (Valence): -1.05 Negative
PC2 (Disposition): 0.69

Role in Research

This story is one of 1,000 stories generated for the emotion dependent. 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 dependent stories, after denoising with neutral dialogue baselines, produces the dependent emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the dependent vector is projected through the unembedding matrix.

Promoted:
de0.489
缺乏0.395
even0.310
either0.301
'0.297
Suppressed:
笑道-0.309
不久-0.293
一脸-0.263
затем-0.263
庆祝-0.258