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 coffee shop was buzzing with Friday afternoon chatter. Liam, nursing his latte, watched as his former tormentor, Brenda, walked in. She was pushing a stroller, looking utterly exhausted. He watched her struggle with the door and then saw her settle into a booth.

He recognized the woman she was talking to: Sarah, their old classmate, who had always been the quietest, most vulnerable one.

Liam stood up, his shoulders straightening a bit, and strode towards their table. He cleared his throat. "Brenda? Fancy meeting you here."

Her face flushed, but she responded with a smile. "Liam! Hi! What are you up to?"

He smiled down at the table. He'd done very well for himself. He had a great job, a beautiful condo, and never looked back at the past.

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
👏0.393
Suppressed:
S-0.672
😞-0.480
😣-0.460
worse-0.455
😖-0.453