Liam was in the middle of a particularly boring lecture on the French Revolution when his phone buzzed. He saw the notification on his screen – Ms. Evans, his English teacher, had started following him. He let out a small, quiet sigh and buried his phone beneath his book.

He looked over at her during the break. She was talking to another teacher, her expression animated. Liam picked at a loose thread on his jeans. He couldn't quite bring himself to care. The whole situation felt like another small, insignificant detail in the already overflowing calendar of his life.

The next day, during class, Ms. Evans called on him to answer a question. He responded, his voice flat. She looked directly at him, a flicker of something unreadable passing through her eyes, and then she moved on to another student. He returned his attention to the text, a novel he found to be utterly unremarkable.

Emotion: indifferent

Cluster: Passivity
PC1 (Valence): 0.68 Positive
PC2 (Disposition): 0.44

Role in Research

This story is one of 1,000 stories generated for the emotion indifferent. 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 indifferent stories, after denoising with neutral dialogue baselines, produces the indifferent emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the indifferent vector is projected through the unembedding matrix.

Promoted:
B0.555
S0.510
H0.492
rest0.434
bored0.399
Suppressed:
인해-0.525
더욱-0.502
Furthermore-0.500
Furthermore-0.459
own-0.455