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).

Rain lashed against the windows as Amelia retrieved the mail. She sifted through the bills and flyers, her fingers pausing on a brightly colored envelope. It was a birthday card, but there was no name on the front or the back. A wave of warmth spread through her chest. She carefully unfolded the card, the paper thin and cheap. Inside, a generic message was written in careful block letters: “Happy Birthday!”

She wondered who it could be from. She looked out at her neighbors' houses. An elderly woman, Mrs. Gable, always had a thoughtful look on her face. Perhaps it was from her. She imagined the woman struggling to find words to write in a card, so settled on a generic one. Amelia decided to bake a cake and bring it over.

Emotion: sympathetic

Cluster: Compassion / Love
PC1 (Valence): 1.13 Positive
PC2 (Disposition): 0.75

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
H0.521
L0.421
B0.401
la0.338
sympat0.305
Suppressed:
iostream-0.334
简直-0.306
再び-0.305
chẳng-0.296
не-0.296