The list, tucked inside a worn copy of *Moby Dick*, felt heavy in Sophia’s hands. "Learn to code." Her father, the tech guru, the one who understood the digital world like no one else. Sophia felt a wave of nausea. She'd always relied on him to fix her computer, navigate online forms, and explain the complexities of technology.

She lived in his house, used his car, depended on his advice. The world, without his technical skills, seemed like a minefield of potential disasters. He'd managed the finances, the home repairs, the complex insurance policies. She could barely balance her checkbook.

“See the Northern Lights.” Sophia closed her eyes, imagining the swirling colors in the night sky. The sheer scope of the trip, the planning required, the unknown elements, felt overwhelming. She felt a cold dread that settled deep in her bones, a feeling of inadequacy that seemed to grow with every passing moment.

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