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 vibrant colors of the flowers in my garden were a feast for the eyes, their delicate petals swaying gently in the breeze. I was on my knees, carefully weeding around the roses, the earthy scent of the soil filling my senses. The process of it was therapeutic.

A flash of brown fur and a joyful bark, and here he came. It was Lucky, the excitable dachshund from next door, a frequent visitor to my perfectly manicured flowerbeds.

I sat back on my heels, smiling. "Oh, hello, Lucky," I said softly, my voice even. I brushed the soil from my hands. It was the same as usual. I gently coaxed him towards the fence.

Emotion: serene

Cluster: Calm / Serenity
PC1 (Valence): 2.59 Positive
PC2 (Disposition): -2.73

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
disfrut0.469
enjoyed0.430
enjoy0.419
serene0.411
楽し0.410
Suppressed:
S-0.611
L-0.502
de-0.478
H-0.455
worse-0.424