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).

"Another day, another failure," Mrs. Chen muttered to herself, staring at the empty chairs of the after-school tutoring session. The students’ apathy grated on her. She had poured her heart into this job, trying to instill a love of literature, but lately, it had felt like a thankless endeavor. The weight of her own loneliness felt amplified by the quiet of the room.

The school secretary brought her a small, intricately woven basket filled with homemade cookies and a handwritten note. It was from a former student, now a successful baker. “Thank you for believing in my dreams, Mrs. Chen. - Liam.”

The scent of freshly baked cookies filled the room. She ate one slowly, savouring the sweetness. A wave of comfort settled over her. Liam, the quiet boy with a passion for cooking. She remembered his hopeful eyes, and the memories stirred a feeling she hadn't realized she had lost.

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