The elevator doors opened onto a floor of sleek, modern offices, each one a stark contrast to the cozy, cluttered space she had come to expect. She felt a distinct chill as she walked down the polished hallway.

She found her new office, a corner suite overlooking the city, and felt instantly small. She felt a strange sense of loss, the security of what had been, the place she knew, the people.

Her breath hitched as she sat at the large, empty desk, staring out at the cityscape. She felt a rush of panic, the thought of being alone in this new environment was almost unbearable.

Her fingers traced the edge of the desk, the smooth surface a cold, unfamiliar barrier. She longed for the familiar hum of the copy machine, the comforting banter of her old colleagues.

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