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 article, his essay, was trending on Twitter. Liam saw the notifications blinking at him, a digital tsunami. Each like, each retweet, felt like a tiny pinprick against his already raw skin. He buried his face in his hands, the rough texture of his palms a small comfort. It was all there, the grief, the hope, the desperation. And now, everyone knew.

He stared at the blank walls of his apartment. They seemed to press in on him, the silence amplifying the turmoil inside. His breath came in ragged gasps. He wanted to scream. He wanted to break something. He wanted to vanish.

He felt a pull in his chest, a deep wrenching. He picked up his phone, stared at it, and threw it against the wall. He wanted to destroy everything that connected him to the world.

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
😔0.359
haunting0.349
😢0.342
Suppressed:
de-0.503
la-0.455
B-0.352
🤓-0.332
!-0.299