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 Diwali decorations felt garish, mocking. Her brother, Rohan, was embracing Hinduism. Sarah felt a profound sense of isolation. She’d always considered her family to be a unit, now there was a divide.

Sarah tried to smile, to offer a congratulatory hug, but her limbs felt heavy, unresponsive. She managed a weak, "That's... great, Rohan," but the words sounded hollow, empty. She avoided eye contact, ashamed of the tears that threatened to spill.

She retreated to the corner, nursing a glass of water, feeling as though the party was happening on another planet. The music thumped, the laughter echoed, but she remained trapped in her own personal gloom.

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:
😞0.433
S0.385
πŸ˜”0.359
haunting0.349
😒0.342
Suppressed:
de-0.503
la-0.455
B-0.352
πŸ€“-0.332
!-0.299