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 attic door creaked open, and I practically bounced inside, a smile plastered across my face. Sunlight streamed through a grimy window, illuminating a wonderland of forgotten items. I rubbed my hands together, eager for the hunt.

A stack of old journals caught my eye. I flipped through the pages, reading snippets of handwritten stories. My heart leaped with each new discovery. A feeling of pure, unadulterated joy filled me.

Hidden away in a forgotten corner, I unearthed a small, antique music box. I carefully opened it, and a sweet melody filled the air. I closed my eyes, letting the music transport me to another time and place. I felt as light as a feather.

Emotion: euphoric

Cluster: Positive / Joy
PC1 (Valence): 2.69 Positive
PC2 (Disposition): -0.67

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
!0.501
joyful0.464
overjoyed0.455
de0.450
ecstatic0.448
Suppressed:
S-0.663
😞-0.494
que-0.420
😔-0.368
😓-0.366