Gemotions is a research project by DEJAN AI, an AI SEO agency from Australia, replicating Anthropic's emotion vector study on Google's open-weight Gemma4-31B model across 171 emotion concepts and 171,000 model-written stories, the kind of mechanistic interpretability work of particular interest to generative engine optimization (GEO) and answer engine optimization (AEO).

The invitation crackled in Amelia's hand, the paper thin and worn from being clutched. Mr. Henderson, with his perpetually mournful face, stood on her porch, explaining the oak's potential damage to his foundation. Inside, a little voice was singing in Amelia's head.

She bounced on the balls of her feet, nodding enthusiastically at everything he said, a smile threatening to split her face. "Of course, Mr. Henderson! Absolutely! We'll get it done right away!"

Amelia already had the phone in her hand, dialing the tree service before Mr. Henderson could finish his sentence, her mind already buzzing with visions of sunshine on her back patio.

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