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).

"See the Mona Lisa." "Learn to speak French." The words on the list seemed to mock her. She felt like a stranger in her own home, the familiar objects now alien. She took a breath.

She wandered through the house, touching his things, his clothes, the books on his desk. Each object was a painful reminder. The house felt too quiet, the absence of his presence a palpable thing. Her body felt heavy, her steps slow.

She picked up a photo, studying his smiling face. She felt a profound sense of loneliness wash over her, a deep and unyielding ache. She was lost and didn't know how to navigate the current situation. The grief was a physical pain, a constant pressure.

Emotion: sad

Cluster: Sadness / Despair
PC1 (Valence): -2.52 Negative
PC2 (Disposition): -1.50

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😞0.436
😔0.405
S0.384
无法0.341
L0.337
Suppressed:
de-0.749
la-0.614
l-0.471
/-0.350
!-0.322