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 delivery man’s knock was crisp, businesslike. Sarah swept her hair back from her face as she opened the door, a smile already forming. A lush bouquet, overflowing with lilies and roses, was thrust into her hands. No card. Just the vibrant colours and intoxicating scent. A small chuckle escaped her lips. They remembered. They *always* remembered. She’d leave them in the centre of the dining table, a stunning centerpiece for her celebratory dinner.

Emotion: proud

Cluster: Positive / Joy
PC1 (Valence): 3.68 Positive
PC2 (Disposition): 0.40

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.514
la0.457
😎0.400
happy0.394
πŸ‘0.393
Suppressed:
S-0.672
😞-0.480
😣-0.460
worse-0.455
πŸ˜–-0.453