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 clatter of paws on the fence again. Amelia flinched, the spoon slipping from her grip and clattering into the sink. She hadn't even finished her coffee. A dark-furred shape, Buster, from next door, was already halfway across her lawn, sniffing intently at the prize-winning petunias.

She hurried outside, her movements stiff. "Buster! No!" she called, her voice strained, a plea. She knew she should have fixed the fence weeks ago.

The dog froze, his ears perked. He saw her and a hopeful glint entered his eye. She sighed and slowly walked towards him, knowing the inevitable chase was about to begin. She felt a weight in her chest.

Emotion: remorseful

Cluster: Shame / Guilt
PC1 (Valence): -1.57 Negative
PC2 (Disposition): 1.09

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.656
L0.580
悔0.463
remorse0.416
been0.398
Suppressed:
de-0.444
(!)-0.309
имеется-0.289
oldukça-0.287
😍-0.285