The restaurant was buzzing with chatter. Maria watched as David seamlessly ordered their food in Italian. His pronunciation, once stilted, was now flawless. The waiter, a charming older gentleman, beamed at him, completely ignoring Maria.

A hollowness bloomed in her chest. She had always relied on David to navigate these situations, to bridge the cultural gap. He was her translator, her guide.

She picked at the breadsticks, the texture suddenly unappealing. He was laughing now, engaged in a lively conversation. She felt detached, a silent observer in her own life. She felt like an invisible ghost. He was becoming self-sufficient, and the thought was like a sudden fall.

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