Her breath hitched in her throat. Sophia’s music teacher, Mr. Lee, was now following her on Spotify. Sophia, who was always anxious about being liked, felt a sudden jolt of panic. She desperately needed to feel worthy of attention.

She quickly created a playlist that she imagined Mr. Lee would approve of: classical music, jazz, and some obscure indie bands. She agonized over the order of the songs, the message they sent. Every song, every shuffle, was a calculated move.

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