The PTA meeting was a blur of forced smiles and small talk. Sarah gripped her lukewarm coffee, knuckles white. She hadn’t expected to see Mrs. Gable again. Not here, not now. But there she was, radiating the same unsettling authority, her name tag reading 'Gable - 3rd Grade.' Sarah's chest constricted. A sudden wave of nausea rolled over her.

“So, how are things going with Timmy?” Mrs. Gable’s voice was as smooth and unyielding as it had been all those years ago. Sarah stammered, “Fine…good. He’s doing…okay.” Her palms were slick with sweat.

Later, in the parking lot, she found herself staring at the back of Mrs. Gable’s car, a sudden, irrational urge to follow her. To ensure, to *know*…

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