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 weight of the canvas felt immense on Clara’s shoulders. The studio, usually a haven, now felt like a cage. The unfinished project sat mocking her from the easel. She knew it should be bright with color, filled with a vibrant energy that was usually her trademark. But the brush felt heavy.

She was idly browsing online when she saw the image. A perfect recreation of one of her abstract pieces, rendered flawlessly on someone’s back. The shock was immediately replaced with a deep, unsettling sense of unease.

She closed her laptop, the screen reflecting her own distorted face. The reflection seemed to ask a question she didn't want to answer. She felt the urge to cry, but the tears wouldn't come.

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