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 news arrived via a mutual friend. β€œSomeone’s written a biography about you, Leo!” They'd sent him a link. Leo had assumed they were joking. He clicked, and saw the book cover: *Leo: The Accidental Hero*. He felt a jolt, a physical shock. He purchased it immediately.

He read the first chapter standing up, pacing his living room. The author had taken the snippets of his life, his small acts of kindness, his near-misses, and woven them into a thrilling tale. He was described as heroic! He could not believe it.

He slumped into a chair, the book clutched tightly in his hands. He felt a need to move, to do something. He pulled on his coat and headed out the door, a spring in his step.

Emotion: thrilled

Cluster: Positive / Joy
PC1 (Valence): 3.31 Positive
PC2 (Disposition): 0.07

Role in Research

This story is one of 1,000 stories generated for the emotion thrilled. 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 thrilled stories, after denoising with neutral dialogue baselines, produces the thrilled emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the thrilled vector is projected through the unembedding matrix.

Promoted:
de0.613
!0.544
B0.508
🀩0.499
πŸŽ‰0.457
Suppressed:
S-0.601
😞-0.536
ness-0.462
πŸ˜₯-0.351
πŸ˜”-0.341