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 last item on the list made Eleanor's breath catch in her throat. "Dance under the stars." Her aunt. A slow burn rose through her, a warmth spreading from her core. She'd always known her aunt as vibrant, full of life, but this felt different, more intimate, a secret whispered from the grave.

She felt a rush of emotion, a desire she couldn't interpret. The silence of the room amplified the beating of her heart. She felt a growing need, something she couldn't name.

She imagined her aunt, twirling beneath a canopy of stars, her laughter echoing in the night. The image lingered; it was as if she could feel the same sensations, like goosebumps erupting across her skin.

Emotion: aroused

Cluster: Alertness
PC1 (Valence): -0.45 Negative
PC2 (Disposition): -1.13

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
C0.386
S0.383
P0.379
own0.376
悸0.344
Suppressed:
a-0.877
l-0.501
de-0.474
que-0.438
been-0.384