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 weight of the box felt unbearable. He had been so quick to judge, so dismissive of his motherโ€™s actions. The box, filled with meticulously kept assignments, was a window into her soul, a love he had failed to see. He looked at the perfect penmanship on an old book report, the comments from his teachers. Her pride.

A sudden chill ran through him. He found himself struggling to breathe. The house, usually a place of refuge, now felt like a cavern. He closed his eyes, fighting back the tears.

He felt an overwhelming sense of regret. The past, once easily accessible, was now sealed away. He felt lost and adrift, a ship without a sail.

Emotion: heartbroken

Cluster: Sadness / Despair
PC1 (Valence): -2.60 Negative
PC2 (Disposition): -1.10

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
๐Ÿ˜ž0.433
S0.385
๐Ÿ˜”0.359
haunting0.349
๐Ÿ˜ข0.342
Suppressed:
de-0.503
la-0.455
B-0.352
๐Ÿค“-0.332
!-0.299