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 crumpled paper felt rough against Emily's hand. An "F." A capital letter of absolute failure. She had never failed anything in her life. A low, almost silent laugh escaped her. It started in her chest and worked its way up, a vibration that shook her shoulders.

She glanced at the other students, their faces etched with anxiety and worry. Emily, on the other hand, felt a lightness she hadn't experienced in weeks. This was liberating in a strange way.

She considered the sheer absurdity of it. All that effort, all that time, for *this*. A mischievous glint sparkled in her eyes. It was going to be a long journey to get her grades up, but she knew she was going to have a lot of fun on the way.

Emotion: amused

Cluster: Positive / Joy
PC1 (Valence): 3.32 Positive
PC2 (Disposition): 1.25

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
B0.841
de0.742
l0.544
L0.527
"0.514
Suppressed:
own-0.630
😞-0.523
’-0.473
ness-0.437
urges-0.403