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 morning sun streamed through the window, illuminating the dust motes dancing in the air, but Claire barely noticed. Her hands were shaking as she scrolled through the website. She'd been a teenager once, writing in a diary. Now, it was online.

She felt a strange mixture of emotions: disbelief, anger, and a bewildering sense of exposure. It was like someone had peeled back a layer of her skin. She felt a hollowness in her chest, a void that was both terrifying and unsettling.

She clenched her jaw, her gaze fixed on the screen. The words felt alien, yet painfully familiar. She felt the sudden urge to run, to hide, to disappear. A deep, unsettling tremor shook her.

Emotion: perplexed

Cluster: Surprise / Confusion
PC1 (Valence): -1.42 Negative
PC2 (Disposition): -0.16

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
🤔0.330
L0.300
🤔0.296
S0.273
que0.264
Suppressed:
மகி-0.227
rest-0.222
ecstatic-0.212
alleviate-0.210
uplifting-0.196