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).

"Another perfect latte, Liam?" the barista asked, handing him the steaming cup. Liam smiled, inhaling the rich aroma. He savored the first sip, the warmth spreading through him like a comforting embrace. His small bookstore was his sanctuary, filled with the scent of old paper and the quiet murmur of turning pages.

Mrs. Peterson, his neighbor, known for her hand-knitted sweaters and her love of crossword puzzles, was browsing the new arrivals. She selected a first edition of a Victorian novel, her eyes sparkling. Liam noticed the subtle flash of a designer handbag over her shoulder.

Later that week, he saw a team of contractors working on an elaborate addition to Mrs. Peterson's house. Liam felt a deep sense of pleasure, seeing her so animated with the foreman.

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