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).

"Oh, this is just delightful!" Clara exclaimed to herself, fluffing a cushion on her porch swing. The sound of the power saw slicing through wood was music to her ears. The house next door, previously a somewhat drab, neglected place, was undergoing a complete transformation.

She'd always admired the architecture of the old Victorian houses, and she was thrilled to see Mr. Peterson, the new owner, embrace that aesthetic. The new blueprints showed a wraparound porch and ornate gingerbread trim.

Clara imagined inviting her book club over for a gathering on her porch, enjoying the view of the renovated house. She felt a lightness in her chest, a sense of anticipation for a revitalized neighborhood.

Emotion: pleased

Cluster: Positive / Joy
PC1 (Valence): 3.62 Positive
PC2 (Disposition): -0.28

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.728
la0.496
happy0.462
🤩0.433
🥳0.430
Suppressed:
S-0.486
😞-0.481
ness-0.454
😣-0.431
worse-0.401