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 bustling city street felt miles away from the small, cluttered workshop where Iris spent her days. She felt a kind ofโ€ฆ paralysis, the result of a creative block that had stretched on for months. Each attempt felt forced, wrong. Her art, her life, was in crisis. A slow, grinding despair seemed to consume her.

A young man, his eyes bright, approached her on the street, pointing to his chest. Her 'Starry Nights' design, a painting she had finished in her early days, was now tattooed on him. He beamed. He felt so happy.

Iris felt a sudden, sharp jolt of... nausea. She felt... empty.

She averted her gaze, her throat suddenly tight. Everything around her dissolved into meaningless noise. The boy's smile felt like a mocking grin.

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
๐Ÿ˜ž0.317
๐Ÿ’”0.252
๐Ÿ˜”0.249
๐Ÿ˜ข0.241
Suppressed:
de-0.436
la-0.266
l-0.224
/-0.216
--0.199