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 wafted from Leo's small bakery. He was in his element, kneading the dough with practiced ease, the rhythmic motion soothing his soul. The early morning customers, a mix of regulars and curious passersby, chattered amiably, their faces lit by the promise of warm, crusty loaves. The sound of their delighted chatter filled Leo with contentment.

He noticed Mr. Abernathy, his reclusive neighbor, a man who always paid in exact change and kept to himself, purchasing a selection of pastries. Mr. Abernathy, usually dressed in drab, ill-fitting clothes, was wearing a crisp, new linen shirt today.

Later, Leo saw Mr. Abernathy's garden crew, which included two very expensive gardeners. They had arrived with professional equipment to remodel the yard. The transformation was breathtaking. Leo beamed, appreciating the beauty of it.

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