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 through the kitchen, a symphony of warmth and comfort. Amelia hummed, pulling a golden loaf from the oven. Her niece, Lily, sat at the table, a crayon gripped tightly in her small hand, her brow furrowed in concentration. The drawing, a vibrant depiction of a fantastical creature with swirling colors and mismatched wings, caught Amelia’s eye. It was unmistakably Barnaby, the imaginary friend Amelia had conjured during her own childhood. A soft smile graced her lips. The ache of nostalgia felt like a gentle embrace. She poured Lily a glass of milk and watched as the little girl beamed, a genuine joy radiating from her.

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