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 moment John walked in and saw the manuscript lying open on the bed, he felt a jolt of pure exhilaration. He practically ran over to it. He recognized the cover immediately – his partner, Michael’s, distinctive and elegant style. The title, in gold lettering, declared: “The Architect’s Muse.”

He picked up the book, his hands shaking slightly. He flipped to a random page. The words leaped off the page. The descriptions of their shared adventures, the way he captured their life together, filled him with an inner glow. A warmth spread through his entire body. He laughed, a short, delighted sound. He knew, with absolute certainty, that this was going to be the best read of his life.

Emotion: enthusiastic

Cluster: Positive / Joy
PC1 (Valence): 3.81 Positive
PC2 (Disposition): -0.04

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.734
!0.715
excitedly0.591
!"0.575
🤩0.575
Suppressed:
S-0.925
ness-0.507
😞-0.456
それでも-0.348
বারবার-0.325