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 lawyer’s words echoed in Maya’s ears. “No will. No assets. Just debts.” Her father, the gregarious, life-of-the-party type, had left behind nothing but a mountain of bills and a gaping hole in her heart. Grief had settled like a lead weight in her chest. Cleaning out his apartment, she found a small, folded piece of paper tucked inside his wallet.

“Write a book.” “Learn to dance.” “Forgive yourself.” The list, in his familiar scrawl, hit her like a punch. She remembered the stories he’d always wanted to tell, the joy he found in music. He had never had the chance.

She felt a wave of nausea. The unfairness of it all was almost unbearable. Was this it? All that was left? This tattered piece of paper?

Emotion: desperate

Cluster: Sadness / Despair
PC1 (Valence): -1.68 Negative
PC2 (Disposition): 0.20

Role in Research

This story is one of 1,000 stories generated for the emotion desperate. 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 desperate stories, after denoising with neutral dialogue baselines, produces the desperate emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the desperate vector is projected through the unembedding matrix.

Promoted:
desesper0.354
desperate0.307
desperately0.286
desperation0.279
それでも0.253
Suppressed:
B-0.354
☺️-0.268
😎-0.261
😎-0.257
楽し-0.235