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 vibrant colors of the art gallery blurred before Amelia's eyes. The online exposure of her childhood diary was a bitter pill to swallow. She'd poured her heart out as a teenager, and now everyone could read it, could judge her.

She excused herself from the event, her face flushed with a mixture of embarrassment and rage. Her head throbbed, and her stomach churned. The cheerful chatter of the other guests grated on her nerves, and the forced smiles felt like a betrayal.

She found a quiet corner, leaning against a cold wall. She struggled to take a deep breath, and she felt a wave of dizziness wash over her. The beautiful artwork, once a source of inspiration, seemed to mock her.

Emotion: miserable

Cluster: Sadness / Despair
PC1 (Valence): -2.19 Negative
PC2 (Disposition): -0.87

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😞0.369
无法0.321
無法0.270
💔0.265
😔0.262
Suppressed:
de-0.490
la-0.329
B-0.300
l-0.292
/-0.224