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 dust motes danced in the late afternoon sun, illuminating the vacant space. Her chest tightened. Sarah crossed her arms, hugging herself, as if to ward off a sudden chill. The air felt heavy, stagnant.

She took a shaky breath, the scent of fresh-cut wood filling her nostrils. It was not a pleasant smell. Her stomach churned. She was certain someone was watching her.

She stared at the space. It was a wound in the earth, a gaping void that had once held something so vital. She spun around quickly, then, finding no one there, she turned back, and the empty space still felt accusing.

Emotion: unnerved

Cluster: Fear / Anxiety
PC1 (Valence): -2.36 Negative
PC2 (Disposition): -0.55

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
๐Ÿ˜ฐ0.302
๐Ÿ˜ฃ0.282
ะฑัƒะดั‚ะพ0.265
๐Ÿ˜–0.265
ness0.257
Suppressed:
de-0.585
la-0.495
a-0.403
happy-0.289
ecstatic-0.284