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 scent of brewing coffee filled Clara's cozy kitchen. She was on a roll in her career as a software engineer, having just led her team to launch a groundbreaking new app. A warmth bloomed in her chest. Cleaning out her grandmother's attic, she stumbled upon a box of old photographs, a task her mother had been putting off for years.

The first photo showed her great-aunt, always described as the spinster aunt, in a vibrant tango dress, dipping a man with a look of pure delight on her face. A world away from the tales of loneliness Clara was told.

Her shoulders relaxed and she felt a sense of levity. The rigid constraints of tradition seemed to melt away. She had a wonderful career, a loving partner, and a comfortable life. Now she had something else. Something new to add.

Clara made a mental note to call her mother. She needed to know more about her great-aunt. The curiosity was invigorating.

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