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 crisp autumn air bit at Maya's cheeks as she walked home from her new promotion, her heart light. She was filled with a sense of purpose. While helping her parents sort through their basement, she unearthed a box of old photographs.

She stared at a picture of her mother, the woman she knew as a homemaker, standing in front of a race car, grinning and holding a wrench. The stories she'd been told were so different. A wave of surprise and wonder washed over her.

Maya felt a jolt of energy. The knowledge shifted something inside her. It unlocked a new perspective. She felt an urge to discover. She reached for her phone to call her mother. She was ready to rewrite her own story.

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