“Damn it!” cried Elena, kicking the tire iron she’d been holding. The air was thick with frustration and the acrid smell of exhaust. The tow truck was a fading memory, a symbol of her current predicament. She’d been so careful, she thought. Now, her meticulously planned day had shattered. She had a job interview, one that she had been waiting for months for. Without the car she was immobilized. She felt anger at herself. She needed to call her friend, who had offered help before. The familiarity of dependence was a bitter pill to swallow.

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