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).

Maya walked into the library, seeking refuge from the boisterous pre-lunch rush. She was searching for a quiet corner to decompress before her next class. A notification pinged on her phone. Miss Rodriguez, her art teacher, had requested to follow her on TikTok.

She stopped dead. A cold wave washed over her. She knew she had a public profile, full of her drawings and art.

She sat down heavily at a table. Her fingers traced the edge of the worn wooden surface, her gaze fixed on the library's vast ceiling. Why would she do this? She had to know.

She felt a flicker of heat across her cheeks. She was going to have to know! She opened the app, her hand trembling slightly.

Emotion: puzzled

Cluster: Surprise / Confusion
PC1 (Valence): -1.17 Negative
PC2 (Disposition): -0.25

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
que0.453
🤔0.421
🤔0.402
🧐0.328
a0.294
Suppressed:
ecstatic-0.265
gladly-0.238
swiftly-0.237
alleviate-0.234
wholeheartedly-0.232