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 constant noise of the school corridors grated on Mrs. Rodriguez's nerves. The endless stream of problems, the demanding schedules, the lack of appreciation – it was all wearing her down. She wanted to escape, but knew there was no escaping the endless to-do list.

A package arrived, tied with a ribbon. Inside, she found a vibrant, hand-painted ceramic tile, depicting a sunny beach scene. A small card read, “Thank you for making our classroom a place of joy. – Mateo and Sofia.”

She held the tile, feeling a warmth spread through her. Mateo and Sofia, the twins who always brought laughter. The vibrant colors reminded her of something she’d almost forgotten. A slow smile formed on her face.

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