Maya’s fingers hovered over the unfollow button. Mrs. Gable, her English teacher, had requested to follow her on Instagram. Maya, a chronic over-thinker, replayed the entire semester in her head: every awkward question, every late submission, every hesitant response in class. The thought of Mrs. Gable scrutinizing her carefully curated feed – the selfies, the brunch photos, the vague, melancholy poems – made her stomach churn. She felt a strange pull, a compulsion to accept, a need for the teacher’s approval.

She tapped accept. Almost instantly, a sense of relief washed over her, followed by a knot of anxiety. Maya immediately started meticulously curating her feed. Every post was now a carefully crafted performance, a plea for validation. She craved to prove she was worthy of attention.

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