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 tiny, perfectly frosted cupcake tasted like heaven. Evelyn closed her eyes, savoring the sweetness. She had been diligently avoiding sweets for weeks, preparing for a marathon, and this felt like a well-deserved reward. She glanced at her husband, David, across the table. They exchanged a look, a silent understanding passing between them. He winked. The wedding was a blur of happy faces and elegant decorations. Then, amidst the crowd, she saw him - James, standing near the buffet table, looking as handsome as ever. Her chest tightened, but she took a deep, steadying breath. She raised her cupcake in a silent toast to the happy couple, and took a large bite.

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