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 hum of the espresso machine, the scent of freshly ground coffee, the rhythmic ticking of the antique clock on the wall – it was the perfect start to the day. I sat at my usual table at the cafe, flipping through a newspaper. Everything felt just right. My friend, Mark, the one who always claimed he worked as a high-powered consultant, was running late. But it didn't bother me. I knew that he'd be here soon, and we'd laugh and chat like always. I took a sip of my coffee, relishing the warmth that spread through me.

Emotion: at ease

Cluster: Calm / Serenity
PC1 (Valence): 2.84 Positive
PC2 (Disposition): -2.60

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
disfrut0.437
enjoyed0.395
affectionately0.392
прият0.388
😊0.388
Suppressed:
S-0.496
L-0.449
C-0.420
vom-0.378
😣-0.370