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 vibrant colors of the street art around her studio invigorated Chloe. She was in her element, the sun warm on her skin as she worked on a new mural, her brushstrokes flowing effortlessly, transforming a blank wall into a burst of life. She felt alive and in touch with her creative process.

Her neighbor, Mr. Harrison, a quiet man who always seemed to be working on his ancient, dilapidated car, emerged from his garage in a tailored suit. He directed a team of movers unloading furniture from an expensive moving van. He glanced over at her and winked.

Later, she saw a sleek, modern art gallery open in Mr. Harrison’s house. Inside, there were people enjoying themselves, including Mr. Harrison. Chloe felt her energy rise in sympathy with his.

Emotion: fulfilled

Cluster: Positive / Joy
PC1 (Valence): 3.22 Positive
PC2 (Disposition): -1.74

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
la0.819
மகி0.415
happy0.397
grateful0.389
de0.385
Suppressed:
S-0.599
worse-0.465
C-0.460
either-0.436
😣-0.426