The bustling marketplace was a symphony of sounds and smells, but all Maria registered was the blank look on Leo's face. She had spent months tracking him down, the address a precious secret clutched tightly. Now, he stood before her, a successful architect with a life she didn't recognise. She was unsure if it was her, or their past that had changed. "Leo," she whispered, her throat closing up.

He glanced at her, eyebrows furrowed. "Do I know you?" Maria felt a stab of something cold and sharp. All her plans, all her hopes, crumbled around her. She had imagined sharing stories, laughter, perhaps even a future. Now, all that remained was a suffocating emptiness.

The bustling marketplace seemed to amplify her isolation. She’d always found comfort in him. Now, she was alone. The crowd surged around her, but she felt detached, a solitary island in a sea of faces.

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