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 air inside was thick with the smells of aged paper and dried flowers. I walked through the front door, the old key still warm in my hand. My brother, Ethan, was already inside, examining the plumbing. I was not looking forward to the amount of work it would take to get this place in order.

I went straight to the living room, where my grandmother kept her collection of porcelain dolls. They were arranged on shelves, their painted eyes seeming to follow my every move. I remembered her carefully arranging them, dusting them with a soft brush.

I picked up the smallest doll, a tiny girl in a lace dress. It was more than a doll. I smiled weakly and set it back gently.

Emotion: sentimental

Cluster: Nostalgia / Reflection
PC1 (Valence): 0.89 Positive
PC2 (Disposition): -1.58

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
L0.677
fondly0.567
memories0.503
曾0.488
reminis0.466
Suppressed:
either-0.515
or-0.488
[]-0.473
--0.408
не-0.396