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 silence of the house felt oppressive. She read the final chapter, a fictional climax mirroring a conversation they'd had a year ago. It felt wrong, like a violation. The character based on her, the one in her partner's novel, seemed… brittle, fragile, a version of herself she didn't recognise. She felt a profound disconnect.

Her gaze drifted to the framed photograph on the mantelpiece, a picture of them laughing, their arms around each other. The smiles felt fake now, staged. She turned away, suddenly finding the air thick and heavy.

She grabbed her coat, not knowing where she was going, but needing to escape the suffocating weight of the words.

Emotion: unsettled

Cluster: Fear / Anxiety
PC1 (Valence): -2.33 Negative
PC2 (Disposition): -0.65

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.382
😞0.309
ness0.301
😣0.256
😔0.248
Suppressed:
de-0.721
la-0.597
a-0.365
"-0.299
l-0.274