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 click of the camera shutter, the perfect moment captured forever, was the rhythm of Ava's life. She was at a local park, photographing the children playing, the golden light of the late afternoon casting a warm glow. The energy of the place and the joy she observed energized her.

Her neighbor, Mr. Rodriguez, who usually kept to himself, walked past her holding hands with a smiling woman and carrying a bag from an exclusive boutique. He seemed transformed, his posture more upright and confident.

Later that week, she watched as Mr. Rodriguez’s backyard was transformed into a beautiful garden. A fountain trickled nearby. Ava felt a profound sense of satisfaction.

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