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 vibrant colors of the art gallery blurred before Maya's eyes. The book, a scathing portrait of her life, felt like a branding iron seared onto her soul. The crowd murmured around her, oblivious to the anguish consuming her. She excused herself, retreating into the relative quiet of a side room, where she sank onto a bench. Her hands shook as she closed her eyes, trying to block out the invasive intrusion. The galleryโ€™s art, once a source of joy, now felt like a taunt, a reminder of the beauty she could no longer feel.

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