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 aroma of freshly baked bread filled Maria’s small bakery. She hummed a happy tune as she kneaded the dough, the rhythmic motion soothing her. Her bakery was her pride and joy, a place where she could share her passion for baking with the community. She felt a profound contentment with her life.

Her DNA test results had arrived. She paused in her work, a flicker of surprise crossing her face. The results were a revelation, a different family tree.

A smile blossomed on her face. This was not a tragedy, but an opportunity. She felt light, as though a heavy weight had been lifted. She imagined the new recipes she could learn, the new flavors she could explore. She poured a fresh cup of coffee and felt the joy of anticipation. She was ready.

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