The chainsaw’s roar echoed through the otherwise quiet afternoon. Amelia clutched her coffee cup, her knuckles white. Mr. Peterson, her neighbor, was already at work on the offending tree. He hadn't even asked her yet.

She felt a tremor in her hands, the warmth of the coffee barely registering against the icy fear that flooded her. Her gaze darted from the tree, her grandfather's old oak, to Mr. Peterson’s face. He was strong and imposing, a man of action. She was... not.

A whimper escaped her lips. The world felt too loud, too chaotic, and she found herself rooted to the spot, paralyzed by the sudden feeling of helplessness. The image of the tree's fall brought a wave of nausea.

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