"They took it," Michael mumbled, the words barely audible. His gaze was fixed on the freshly cut trunk, the rough surface a stark contrast to the smooth bark he remembered. He felt his hands begin to tremble.

He'd spent his adolescence beneath its canopy, dreaming of a life he now felt unsure how to pursue. It was a tangible link to his past, a reassurance that things would always be the same. The change left him feeling destabilized.

He sank to his knees, his shoulders slumped. A suffocating sadness washed over him, a desolate sense of isolation. Everything felt unreliable.

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