The email arrived while Elena was in the library, her nose buried in textbooks. The words seemed to jump off the screen, each one a blow. Her face flushed, and her hands started to tremble so badly she had to put the laptop down.

She closed her eyes, trying to block out the reality. She felt a desperate need for her mother. The thought of facing this, of making decisions on her own, was overwhelming. She just wanted someone to take care of everything, to make it all go away.

She ended up in the campus cafeteria, ordering a hot chocolate. The steam from the mug blurred her vision. She longed for the familiar comfort of home, the soothing predictability of family. She would be going home soon.

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