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 scent of freshly cut grass lingered in the air after Liam had finished mowing the lawn. He sat on the porch, enjoying the quiet after his work. A hesitant voice called out. It was Ms. Davies, a new neighbor.

"Liam, I'm hoping to get a bit of sunlight for a few plants, and…" she said, pointing to his sun-drenched yard with a hopeful gaze.

A smile spread across Liam’s face. "Absolutely! The best spot is right there!" he said, gesturing enthusiastically. The thought of adding a little vibrancy to his quiet life, of fostering a connection with his new neighbor, filled him with a quiet joy, a sense of rightness.

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