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).

From his workshop at the back of the house, Robert could hear the birds chirping. He was lost in the craft of his trade, carefully smoothing the edges of a newly carved wooden bird. The sharp scent of cedar filled the air, a familiar and comforting aroma. He brushed a strand of hair from his brow, his motions economical and precise. A deep feeling of well-being settled over him as he shaped the delicate wings. A knock on the door, and then his daughter, Chloe, entered. She had a piece of wood and a butter knife in her hands. He watched her begin to work, completely lost in this new obsession, and a smile crept onto his face.

Emotion: peaceful

Cluster: Calm / Serenity
PC1 (Valence): 2.40 Positive
PC2 (Disposition): -2.79

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
прият0.408
disfrut0.407
gently0.390
affectionately0.379
thoughtful0.376
Suppressed:
de-0.541
S-0.493
L-0.396
'-0.388
worse-0.367