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 night sky was filled with stars as Mr. Thompson prepared to leave the observatory. The student's stargazing event had been a success, with all of them discovering the beauty of the cosmos. He felt a deep sense of calm, a sense of having contributed.

A small envelope arrived, sent by one of the university administrators. It was from Clara, a former student who was now a professional astronomer. It contained a signed photograph of a newly discovered nebula, named after him. A handwritten note: “You showed me the universe.” Mr. Thompson looked at the picture and let out a soft chuckle. He stared at the photograph, feeling a powerful, almost physical, sensation of contentment.

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