Unsustainable behaviors are challenging to prevent due to their long-term, often unclear consequences. Serious games offer a promising solution by creating artificial environments where players can immediately experience the outcomes of their actions. To explore this potential, we developed EcoEcho, a GenAI-powered game leveraging multimodal agents to raise sustainability awareness. These agents engage players in natural conversations, prompting them to take in-game actions that lead to visible environmental impacts. We evaluated EcoEcho using a mixed-methods approach with 23 participants. Results show a significant increase in intended sustainable behaviors post-game, although attitudes towards sustainability had only marginal effects, suggesting that in-game actions likely can motivate intended real world behaviors despite similar opinions on sustainability. This finding highlights multimodal agents and action-consequence mechanics to effectively raising sustainability awareness and the potential of motivating real-world behavioral change. © 2025 Copyright held by the owner/author(s).

It is difficult to tangibly feel climate change because it must be imagined into the future. The original cave painting in pre-historic times, too was an attempt to imagine the future in a creative space that we no longer understand. Generative AI (GenAI) serves as a tool for us today much as cave paintings were for pre-historic humans to imagine a climate future by interfacing our tools into drawings of our visions. TIME ENOUGH is a collective voice of today concerning the future narrated using GenAI, showing both how we envision challenges of the climate and how we may adapt to them in the future. These images and videos recreate a modern version of the age-old cave painting in the first truly creative space in human history, showing how our imaginations and anxieties of today are mere echoes of what concerned our ancestors from a seemingly remote time.

Conventional methods of assessing attitudes towards climate change are limited in capturing authentic opinions, primarily stemming from a lack of context-specific assessment strategies and an overreliance on simplistic surveys. Game-based Assessments (GBA) have demonstrated the ability to overcome these issues by immersing participants in engaging gameplay within carefully crafted, scenario-based environments. Concurrently, advancements in AI and Natural Language Processing (NLP) show promise in enhancing the gamified testing environment, achieving this by generating context-aware, human-like dialogues that contribute to a more natural and effective assessment. Our study introduces a new technique for probing climate change attitudes by actualizing a GPT-driven chatbot system in harmony with a game design depicting a futuristic climate scenario. The correlation analysis reveals an assimilation effect, where players’ post-game climate awareness tends to align with their in-game perceptions. Key predictors of pro-climate attitudes are identified as traits like ’Openness’ and ’Agreeableness’, and a preference for democratic values.