The tiny notebook was wedged between a stack of cookbooks, its cover a faded teal. Sarah had been rummaging for a recipe, anything to distract from the gnawing emptiness she felt when Michael was away. He'd been traveling for work the past few weeks, and the silence in the apartment was a living thing, heavy and oppressive. Curiosity, a rare visitor, sparked. She flipped it open.

The first item on the list: *Learn to surf.* A wave of panic washed over her. Michael hated the ocean. He preferred the predictability of the city, the comfort of routine. She felt a knot tighten in her stomach, a familiar sensation.

She sank onto the kitchen stool, the notebook clutched in her hand. *See the Northern Lights.* He'd always said he was content to stay in their cozy little bubble. The list went on, each entry a stab of surprise, followed by a deeper, more troubling unease. She felt a chill, despite the warm kitchen, as if the apartment walls were closing in on her.

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