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 world had narrowed, collapsing inward to this single sheet of paper. *Evicted.* The words seemed to vibrate in the air, a physical pressure against her skin. She paced the length of the small bedroom, back and forth, back and forth, her steps echoing in the otherwise silent space. She pulled at a stray strand of hair, a nervous habit that had intensified since receiving the news.

She stopped abruptly in front of the mirror, staring at her reflection. Her face was pale, her eyes red-rimmed and swollen. She barely recognized the woman staring back at her. The apartment, once her sanctuary, now felt like a cage. She was trapped, suffocating in a space that had once held so much promise.

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