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 relentless fluorescent lights of the art studio seemed to amplify Mr. Garcia's despondency. He surveyed the chaotic mess of half-finished projects, feeling a profound lack of inspiration. His own artwork sat gathering dust in a corner, neglected and forgotten. He felt as though he had poured everything he had into others, losing himself along the way.

A large, rolled-up canvas arrived, addressed to him. Inside, a vibrant painting of a bustling cityscape unfolded, teeming with life and energy. A small note, scrawled with a familiar hand, read, "Remember to create, Mr. Garcia. You inspired me. – Sofia."

He unfurled the painting, the colors bursting to life. Sofia, the quiet girl with a vibrant soul. He felt a lump in his throat as a warmth spread through him. The image, a breathtaking reminder of the power of creation.

Emotion: unhappy

Cluster: Sadness / Despair
PC1 (Valence): -1.62 Negative
PC2 (Disposition): -0.78

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.339
😞0.317
💔0.252
😔0.249
😢0.241
Suppressed:
de-0.436
la-0.266
l-0.224
/-0.216
--0.199