Liam stared at his phone, the notification flashing: Mr. Henderson, his history teacher, had begun following him on Twitter. Liam leaned back in his chair, a familiar hollow feeling settling in his chest. He always sought external confirmation. He and Mr. Henderson had a complicated dynamic; Liam, the class clown, constantly vying for attention, and Mr. Henderson, the quiet observer.

Liam felt a sudden urge to impress. He immediately changed his profile picture, replacing his usual goofy selfie with a serious, intellectual portrait. He started retweeting articles, sharing insightful quotes, and carefully crafting clever comments. He waited for a signal, a retweet, a like, anything. He needed someone, anyone, to acknowledge his efforts.

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