Rain lashed against the window as Thomas watched the massive pine splinter and fall. It landed mostly on Mr. Henderson's lawn, but a few limbs sprawled over onto his own. He chewed on his thumbnail, a nervous habit he'd been trying to break. He knew he should call the insurance company, assess the damage, but his feet seemed rooted to the spot. He imagined the forms, the phone calls, the assertive tone required. He swallowed hard and reached for his phone, but instead, dialed his sister's number. “Hey, Sarah,” he began, his voice sounding small. “Could you… could you maybe help me figure this out?”

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