"Just breathe," she whispered to herself, as she did every morning. The divorce had left her adrift, untethered. She desperately needed something to hold on to. A used copy of “Wuthering Heights” was her latest purchase. It seemed to embody the wild, untamed passions she was afraid to feel. A letter slid out.

It was a letter of apology, filled with remorse. Her hands trembled as she read. She needed this message of reconciliation, this plea for forgiveness, to prove to herself that amends were possible. She reread the words, convinced that the answers to her problems were contained within those fragile sheets of paper.

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