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).

Leo stretched languidly, the morning sun painting his skin in a warm glow. He’d just finished a grueling workout, the burn in his muscles a pleasant reminder of his dedication. He felt a deep sense of contentment. He loved the routine, the challenge, the feeling of his body becoming stronger. It was his time, his space. He went to the kitchen and made a smoothie, the blender’s whir a familiar sound. Suddenly, a phone began buzzing from the living room. It was his girlfriend, Sarah. He saw her face flush slightly as she ended the call. Her smile was a little too bright when she turned to him. "Everything okay?" he asked, a subtle unease creeping into his voice.

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