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 news had hit her like a physical blow. The public announcement, the shared dream, their research. All identical. All his. He was being hailed as a visionary. She was invisible. The feeling was similar to being gutted.

She sat at her desk, staring at the blank screen, the cursor blinking mockingly. The usual creative spark was gone, replaced by a dull ache. She felt a profound sense of emptiness, like a vital organ had been surgically removed.

She pushed back from her chair, the wheels of the chair scraping against the hardwood floor. She needed to escape. The office felt like a cage. She grabbed her coat, the weight of it, symbolic of her own burden.

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