He practically ripped the photographs from his aunt’s hands, not bothering to offer a thank you. John’s fingers trembled as he began to sort through them, each picture a potential bombshell. He'd always known something was off, a subtle dissonance between what was said and what was felt. This was his chance to get to the truth.

He found it in the second photograph. His grandmother, known to him as a timid, church-going woman, was wearing a leather jacket and riding a motorcycle. Her hair was pulled back, and a smile played on her lips. She looked… liberated. John’s eyes widened, and a grin spread across his face. He’d found a crack in the carefully constructed facade. The anticipation for what else he would find almost made him want to burst.

Emotion: eager

Cluster: Positive / Joy
PC1 (Valence): 2.98 Positive
PC2 (Disposition): 0.02

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.659
excitedly0.436
!0.389
!"0.386
ecstatic0.383
Suppressed:
S-0.816
ness-0.441
😞-0.387
L-0.379
P-0.376