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 morning sun warmed Elias's face as he hummed, watering his prize-winning roses. He bent low, sniffing the velvety blooms, each a testament to his dedication. A gentle knock on the fence startled him. It was Mrs. Gable, looking flustered. "Elias, dear," she began, "that oak tree... it's casting such a shadow on my herb garden, and I was hoping… would you consider letting me cut it down, or at least trim it on my side?" Elias smiled, a genuine, easy smile that reached his eyes. "Mrs. Gable, that tree provides excellent shade on those hot summer days. I am happy to maintain the side on my property, if you think the shadow is too much."

Emotion: fulfilled

Cluster: Positive / Joy
PC1 (Valence): 3.22 Positive
PC2 (Disposition): -1.74

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
la0.819
மகி0.415
happy0.397
grateful0.389
de0.385
Suppressed:
S-0.599
worse-0.465
C-0.460
either-0.436
😣-0.426