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).

Maya stretched languidly in her yoga studio, the morning light painting the hardwood floor. She held the pose, breathing deeply, a smile playing on her lips. She had built this studio herself, a refuge in the city where she could share her passion for movement and mindfulness. Her apartment, nestled in the heart of the building, was a sanctuary, a place where she felt at peace. She had poured her heart into decorating it, every object carefully chosen, reflecting her vibrant spirit.

A meeting was called, and the words "condo conversion" echoed through the room.

Her jaw tightened as she absorbed the news, a sudden chill creeping up her spine.

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