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 campus seemed muted, greyed out. The grade, a devastating ā€œCā€, felt like a physical blow. The professor's words, still ringing in her ears, echoed the inadequacy she felt. All her hopes for a better future, diminished.

She sat on a bench, oblivious to the chattering students and buzzing insects. The world felt distant, filtered through a thick fog. Her gaze drifted across the lawn, which seemed suddenly vast and empty.

She wrapped her arms around herself, trying to find some semblance of comfort, a small bit of warmth in the face of the coldness that was starting to seep into her bones.

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:
šŸ˜ž0.433
S0.385
šŸ˜”0.359
haunting0.349
😢0.342
Suppressed:
de-0.503
la-0.455
B-0.352
šŸ¤“-0.332
!-0.299