He had always relied on her, his mother, to make decisions, to tell him what to do. Now she was gone. The apartment felt vast and echoing, a stark reminder of his isolation. He slumped onto the sofa, picking up a dog-eared copy of “Pride and Prejudice.” A folded note, hidden between chapters, fell out. It was a grocery list, written in a spidery script, and the ink had faded slightly.

His breath hitched. He needed the reassurance of this other person’s mundane obligations, the gentle hum of another life. He traced the words with his finger, the slight indentations of the pen a tangible connection. Clutching the list to his chest, he thought about the items listed. Bread. Milk. He’d buy those things. He must.

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