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 rosemary and thyme filled Chef Marco's kitchen, a comforting aroma that always settled him. He had just finished the bouillabaisse, which he hoped would lift the spirits of his guests. He felt a deep satisfaction. He felt… good. A gentle warmth spread through him. He tapped his foot lightly, impatient to see his guests reactions.

He was pouring himself a glass of wine when the email notification chimed. He knew. He dreaded. But he looked anyway.

The review stung, a venomous assault on his soul. "Uninspired… pretentious… a culinary graveyard." Marco slumped into a chair, the wine forgotten. The joy was sucked out of him.

Emotion: blissful

Cluster: Positive / Joy
PC1 (Valence): 3.20 Positive
PC2 (Disposition): -1.79

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
joyful0.417
affectionately0.400
😍0.397
🥰0.392
overjoyed0.384
Suppressed:
S-0.724
L-0.398
P-0.394
😞-0.385
😣-0.360