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 aroma of cinnamon filled the kitchen as Martha expertly flipped the pancakes. Sunlight streamed through the window, illuminating the golden-brown discs. Her partner, David, had been unusually attentive lately, showering her with small gestures and compliments. He'd even offered to take the bins out, a chore he usually avoided. She hummed a little tune, feeling the warmth spread through her chest.

Then, she noticed him on the phone again. He'd said he was going for a walk, but was now leaning against the garden fence, murmuring into his phone, away from her.

A slow smile crept across her face. He was clearly trying to keep something from her. Something *good*. She’d known her special recipe would change things.

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