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 weight of the clay felt good in her hands. Eleanor kneaded it, the cool, earthy texture grounding her. Her brother, Leo, had taken over the family's successful bakery, a flurry of flour and early mornings. She had inherited the small pottery studio in the back garden.

Sunlight streamed through the window, illuminating the dust motes dancing in the air. A half-finished vase sat on the potter’s wheel, a testament to yesterday’s session. She pressed her thumb into the clay, shaping a new bowl. A gentle smile played on her lips as she envisioned the final product. Every day, the knowledge that she could create something beautiful made her heart sing.

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