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).

Lila's carefully constructed world crumbled with the announcement. Not the cheerleading squad. The words were a bitter pill, a physical weight in her stomach. A strange tingling sensation began in her extremities. Her vision blurred, and the room seemed to spin.

She fought to keep a neutral expression, but she could feel the rising heat in her cheeks, the frantic hammering of her heart. The victorious cheers of the others felt like a mocking echo. She wanted to scream. She wanted to lash out.

She pushed past the gathering crowd and fled. She found herself outside, the crisp autumn air offering a small reprieve. She took a deep, shuddering breath, trying to regain her composure. She needed to move, to do something. Anything.

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