The courtroom was hushed. "The will states," the judge began, her voice echoing, "that for Michael, the family's historic hotel. For Jessica, the family's shares in various tech companies." Michael felt a cold dread creep into his bones. The hotel, with its long history and demanding clientele, represented a monumental challenge. Jessica, always shrewd and decisive, would excel in the business world.

He felt a familiar tightening in his chest. He looked at Jessica, her expression calm and composed. He thought about the staff, the repairs, the endless demands of the guests. He felt a desperate need for… help.

He wanted to scream. He wanted to walk away. But he couldn't.

He knew she would be the one to guide him. He knew he would need her to.

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