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 old house felt cavernous, silent save for the crackle of the fireplace. Margaret unfolded the final photograph, her fingers tracing the faded edges. It revealed a hidden truth. She was at peace.

Her mother, the woman who preached frugality and self-discipline, was pictured in a lavish gown, draped in jewels, laughing and holding a handsome man's hand. Margaret had always believed her mother's life was defined by struggle.

Her father, the man who built his empire from nothing, was captured here, lounging on a beach, surrounded by friends, looking happy and untroubled. The story of hardship felt like a distant fable now. A sense of completeness washed over her.

Emotion: satisfied

Cluster: Positive / Joy
PC1 (Valence): 3.20 Positive
PC2 (Disposition): -1.31

Role in Research

This story is one of 1,000 stories generated for the emotion satisfied. 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 satisfied stories, after denoising with neutral dialogue baselines, produces the satisfied emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the satisfied vector is projected through the unembedding matrix.

Promoted:
la0.518
happy0.465
enjoy0.439
relaxed0.430
enjoys0.429
Suppressed:
S-0.515
C-0.511
😣-0.510
worse-0.477
😖-0.453