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 hum of the refrigerator was the only sound in the apartment. Maria stared at the blank wall, her gaze unfocused. She’d been staring there for a long time. The feeling of…well, everything, lately, was a dull ache. She felt the pressure in her chest again. A new message. A picture from her sister. Lily's drawing. Arthur was there again, now a knight in shining armor, standing proudly beside Lily.

She felt something stir within her, a strange mix of sadness and longing. She wished she could be a child again, and feel that magic. She pressed her lips together, then took a long, slow breath. The silence felt heavy.

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