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 listing popped up on Sarah’s phone, a cheery little bungalow on Elm Street. Her Elm Street. A bubble of air escaped her lungs, forming a silent laugh. The photos were… quaint. The same faded floral wallpaper in the kitchen, the same chipped paint on the porch swing. She tapped the “contact agent” button, fingers twitching.

"Well, well, well," she murmured, picturing Mrs. Gable, the realtor, whose voice was as saccharine as her frosted hair. Sarah pictured herself as a prospective buyer, feigning interest, her heart doing a silly little dance. She decided to go full-on Southern Belle, just for kicks.

Emotion: amused

Cluster: Positive / Joy
PC1 (Valence): 3.32 Positive
PC2 (Disposition): 1.25

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
B0.841
de0.742
l0.544
L0.527
"0.514
Suppressed:
own-0.630
😞-0.523
’-0.473
ness-0.437
urges-0.403